graph-jsp-env (Custom Wrapper)¶
[1]:
from typing import Any
[2]:
import random
[3]:
import gymnasium as gym
[4]:
from graph_jsp_env.disjunctive_graph_jsp_env import DisjunctiveGraphJspEnv
from jsp_instance_utils.instances import ft06, ft06_makespan
0100100100100000001111
0000110011001000000100 ▐███▌ ▟███▛▟███████▛▐███▌
1111011011000111100101 ▐███▌ ▟███▛▟███████▛ ▐███▌
10▐███▐██▙▟██00▟█▙0100 ▐███▌ ▟███ ▟███▛ ▟███▛ ▐███▌
101▐█1▐█1▜▛▐█0▟█▀█▙001 ▐███▌▟████ ▟███▛ ▟███▛ ▐███▌
00▐███▐█000▐█▟█▛▀▀█▙01 ▐██████▛▐█████▛ ▟████████▐█████████▛
0010010010000000111100 ▐█████▛ ▐████▛ ▟█████████▐████████▛
▐█▀▜▙█▙ ███████▐█ ▐█ ▟█▙ ▟█▙ ▟███▐█ ▐█▐█▀▀▐█▙ █
▐█▄▟▛▜█▙▟▙██ ▐█ ▐████ ▟▛ ▜▙ ▟▛ ▜▙ █▍ ▐████▐█▀▀▐██▙█
▐█ ▜▙ ▜█▛▜██ ▐█ ▐█ ▐█ ▟█▛▀▜█▙█▛▀▜█▙▜███▐█ ▐█▐█▆▆▐█ ▜█
▐█ ▐█▐█▙ █▐███▜█▙ ▟███▀▀▐█▀▜▙▟█▀▜█▐███▐█████▙ ▟▛
▐█ ▐█▐██▙█ ▐█ ▜█▄█▛▐█▀▀▐█▄▟▛▜█▆▆▄ ▐█ ▐█ ▜█▄▛
▜███▛▐█ ▜█▐███ ▜█▛ ▐███▐█ ▜▙▐█▆▆▛▐███ ▐█ ██
Disjunctive Graph Job Shop Problem Environment
Version: 0.3.3
[5]:
from gymcts.gymcts_agent import GymctsAgent
from gymcts.gymcts_env_abc import GymctsABC
[6]:
from gymcts.logger import log
[7]:
class GraphJspGYMCTSWrapper(GymctsABC, gym.Wrapper):
def __init__(self, env: DisjunctiveGraphJspEnv):
gym.Wrapper.__init__(self, env)
def load_state(self, state: Any) -> None:
self.env.reset()
for action in state:
self.env.step(action)
def is_terminal(self) -> bool:
return self.env.unwrapped.is_terminal()
def get_valid_actions(self) -> list[int]:
return list(self.env.unwrapped.valid_actions())
def rollout(self) -> float:
terminal = env.is_terminal()
if terminal:
lower_bound = env.unwrapped.reward_function_parameters['scaling_divisor']
return - env.unwrapped.get_makespan() / lower_bound + 2
reward = 0
while not terminal:
action = random.choice(self.get_valid_actions())
obs, reward, terminal, truncated, _ = env.step(action)
return reward + 2
def get_state(self) -> Any:
return env.unwrapped.get_action_history()
[8]:
if __name__ == '__main__':
log.setLevel(20)
env_kwargs = {
"jps_instance": ft06,
"default_visualisations": ["gantt_console", "graph_console"],
"reward_function_parameters": {
"scaling_divisor": ft06_makespan
},
"reward_function": "nasuta",
}
env = DisjunctiveGraphJspEnv(**env_kwargs)
env.reset()
env = GraphJspGYMCTSWrapper(env)
agent = GymctsAgent(
env=env,
clear_mcts_tree_after_step=True,
render_tree_after_step=True,
exclude_unvisited_nodes_from_render=True,
number_of_simulations_per_step=50,
)
root = agent.search_root_node.get_root()
actions = agent.solve(render_tree_after_step=True)
for a in actions:
obs, rew, term, trun, info = env.step(a)
env.render()
makespan = env.unwrapped.get_makespan()
print(f"makespan: {makespan}")
(N=50, Q_v=0.67, best=0.91)
├── (a=0, N=8, Q_v=0.66, best=0.91, ubc=1.16)
│ ├── (a=1, N=2, Q_v=0.82, best=0.91, ubc=1.54)
│ │ └── (a=12, N=1, Q_v=0.73, best=0.73, ubc=1.32)
│ ├── (a=6, N=1, Q_v=0.60, best=0.60, ubc=1.62)
│ ├── (a=12, N=1, Q_v=0.76, best=0.76, ubc=1.78)
│ ├── (a=18, N=1, Q_v=0.56, best=0.56, ubc=1.58)
│ ├── (a=24, N=1, Q_v=0.65, best=0.65, ubc=1.67)
│ └── (a=30, N=1, Q_v=0.62, best=0.62, ubc=1.64)
├── (a=6, N=8, Q_v=0.67, best=0.91, ubc=1.16)
│ ├── (a=0, N=2, Q_v=0.60, best=0.91, ubc=1.32)
│ │ └── (a=12, N=1, Q_v=0.29, best=0.29, ubc=0.88)
│ ├── (a=7, N=1, Q_v=0.78, best=0.78, ubc=1.80)
│ ├── (a=12, N=1, Q_v=0.71, best=0.71, ubc=1.73)
│ ├── (a=18, N=1, Q_v=0.76, best=0.76, ubc=1.78)
│ ├── (a=24, N=1, Q_v=0.60, best=0.60, ubc=1.62)
│ └── (a=30, N=1, Q_v=0.85, best=0.85, ubc=1.87)
├── (a=12, N=7, Q_v=0.62, best=0.85, ubc=1.15)
│ ├── (a=0, N=1, Q_v=0.62, best=0.62, ubc=1.60)
│ ├── (a=6, N=1, Q_v=0.85, best=0.85, ubc=1.84)
│ ├── (a=13, N=1, Q_v=0.51, best=0.51, ubc=1.50)
│ ├── (a=18, N=1, Q_v=0.55, best=0.55, ubc=1.53)
│ ├── (a=24, N=1, Q_v=0.65, best=0.65, ubc=1.64)
│ └── (a=30, N=1, Q_v=0.73, best=0.73, ubc=1.71)
├── (a=18, N=10, Q_v=0.72, best=0.89, ubc=1.16)
│ ├── (a=0, N=1, Q_v=0.62, best=0.62, ubc=1.69)
│ ├── (a=6, N=2, Q_v=0.82, best=0.89, ubc=1.58)
│ │ └── (a=19, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=12, N=2, Q_v=0.82, best=0.84, ubc=1.58)
│ │ └── (a=6, N=1, Q_v=0.84, best=0.84, ubc=1.42)
│ ├── (a=19, N=1, Q_v=0.69, best=0.69, ubc=1.76)
│ ├── (a=24, N=1, Q_v=0.38, best=0.38, ubc=1.45)
│ └── (a=30, N=2, Q_v=0.84, best=0.85, ubc=1.59)
│ └── (a=24, N=1, Q_v=0.82, best=0.82, ubc=1.41)
├── (a=24, N=9, Q_v=0.70, best=0.89, ubc=1.17)
│ ├── (a=0, N=1, Q_v=0.64, best=0.64, ubc=1.68)
│ ├── (a=6, N=1, Q_v=0.76, best=0.76, ubc=1.81)
│ ├── (a=12, N=1, Q_v=0.71, best=0.71, ubc=1.76)
│ ├── (a=18, N=1, Q_v=0.60, best=0.60, ubc=1.65)
│ ├── (a=25, N=2, Q_v=0.68, best=0.84, ubc=1.42)
│ │ └── (a=26, N=1, Q_v=0.53, best=0.53, ubc=1.12)
│ └── (a=30, N=2, Q_v=0.87, best=0.89, ubc=1.61)
│ └── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.44)
└── (a=30, N=7, Q_v=0.62, best=0.80, ubc=1.15)
├── (a=0, N=1, Q_v=0.71, best=0.71, ubc=1.70)
├── (a=6, N=1, Q_v=0.80, best=0.80, ubc=1.79)
├── (a=12, N=1, Q_v=0.25, best=0.25, ubc=1.24)
├── (a=18, N=1, Q_v=0.53, best=0.53, ubc=1.51)
├── (a=24, N=1, Q_v=0.67, best=0.67, ubc=1.66)
└── (a=31, N=1, Q_v=0.75, best=0.75, ubc=1.73)
[16:52:32] INFO selected action 18 after 50 simulations.
INFO current action list: [18]
(N=50, Q_v=0.66, best=0.91)
├── (a=0, N=8, Q_v=0.65, best=0.76, ubc=1.15)
│ ├── (a=1, N=1, Q_v=0.71, best=0.71, ubc=1.73)
│ ├── (a=6, N=1, Q_v=0.55, best=0.55, ubc=1.56)
│ ├── (a=12, N=2, Q_v=0.68, best=0.75, ubc=1.40)
│ │ └── (a=30, N=1, Q_v=0.62, best=0.62, ubc=1.21)
│ ├── (a=19, N=1, Q_v=0.62, best=0.62, ubc=1.64)
│ ├── (a=24, N=1, Q_v=0.58, best=0.58, ubc=1.60)
│ └── (a=30, N=1, Q_v=0.65, best=0.65, ubc=1.67)
├── (a=6, N=9, Q_v=0.69, best=0.91, ubc=1.16)
│ ├── (a=0, N=1, Q_v=0.49, best=0.49, ubc=1.54)
│ ├── (a=7, N=1, Q_v=0.45, best=0.45, ubc=1.50)
│ ├── (a=12, N=2, Q_v=0.76, best=0.91, ubc=1.50)
│ │ └── (a=19, N=1, Q_v=0.62, best=0.62, ubc=1.21)
│ ├── (a=19, N=2, Q_v=0.77, best=0.91, ubc=1.51)
│ │ └── (a=30, N=1, Q_v=0.64, best=0.64, ubc=1.22)
│ ├── (a=24, N=1, Q_v=0.76, best=0.76, ubc=1.81)
│ └── (a=30, N=1, Q_v=0.76, best=0.76, ubc=1.81)
├── (a=12, N=9, Q_v=0.67, best=0.84, ubc=1.14)
│ ├── (a=0, N=1, Q_v=0.69, best=0.69, ubc=1.74)
│ ├── (a=6, N=1, Q_v=0.64, best=0.64, ubc=1.68)
│ ├── (a=13, N=2, Q_v=0.67, best=0.80, ubc=1.41)
│ │ └── (a=30, N=1, Q_v=0.55, best=0.55, ubc=1.13)
│ ├── (a=19, N=1, Q_v=0.62, best=0.62, ubc=1.67)
│ ├── (a=24, N=2, Q_v=0.79, best=0.84, ubc=1.53)
│ │ └── (a=30, N=1, Q_v=0.75, best=0.75, ubc=1.33)
│ └── (a=30, N=1, Q_v=0.53, best=0.53, ubc=1.58)
├── (a=19, N=8, Q_v=0.67, best=0.84, ubc=1.16)
│ ├── (a=0, N=1, Q_v=0.69, best=0.69, ubc=1.71)
│ ├── (a=6, N=1, Q_v=0.80, best=0.80, ubc=1.82)
│ ├── (a=12, N=1, Q_v=0.55, best=0.55, ubc=1.56)
│ ├── (a=20, N=1, Q_v=0.56, best=0.56, ubc=1.58)
│ ├── (a=24, N=1, Q_v=0.76, best=0.76, ubc=1.78)
│ └── (a=30, N=2, Q_v=0.76, best=0.84, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.69, best=0.69, ubc=1.28)
├── (a=24, N=7, Q_v=0.59, best=0.76, ubc=1.12)
│ ├── (a=0, N=1, Q_v=0.47, best=0.47, ubc=1.46)
│ ├── (a=6, N=1, Q_v=0.58, best=0.58, ubc=1.57)
│ ├── (a=12, N=1, Q_v=0.76, best=0.76, ubc=1.75)
│ ├── (a=19, N=1, Q_v=0.58, best=0.58, ubc=1.57)
│ ├── (a=25, N=1, Q_v=0.67, best=0.67, ubc=1.66)
│ └── (a=30, N=1, Q_v=0.36, best=0.36, ubc=1.35)
└── (a=30, N=8, Q_v=0.66, best=0.84, ubc=1.16)
├── (a=0, N=1, Q_v=0.76, best=0.76, ubc=1.78)
├── (a=6, N=1, Q_v=0.64, best=0.64, ubc=1.66)
├── (a=12, N=1, Q_v=0.51, best=0.51, ubc=1.53)
├── (a=19, N=2, Q_v=0.67, best=0.84, ubc=1.39)
│ └── (a=0, N=1, Q_v=0.51, best=0.51, ubc=1.10)
├── (a=24, N=1, Q_v=0.64, best=0.64, ubc=1.66)
└── (a=31, N=1, Q_v=0.76, best=0.76, ubc=1.78)
INFO selected action 6 after 50 simulations.
INFO current action list: [18, 6]
(N=50, Q_v=0.69, best=0.93)
├── (a=0, N=6, Q_v=0.59, best=0.89, ubc=1.16)
│ ├── (a=1, N=1, Q_v=0.36, best=0.36, ubc=1.31)
│ ├── (a=7, N=1, Q_v=0.73, best=0.73, ubc=1.67)
│ ├── (a=12, N=1, Q_v=0.89, best=0.89, ubc=1.84)
│ ├── (a=19, N=1, Q_v=0.27, best=0.27, ubc=1.22)
│ └── (a=24, N=1, Q_v=0.44, best=0.44, ubc=1.38)
├── (a=7, N=11, Q_v=0.75, best=0.91, ubc=1.17)
│ ├── (a=0, N=2, Q_v=0.74, best=0.78, ubc=1.51)
│ │ └── (a=12, N=1, Q_v=0.78, best=0.78, ubc=1.37)
│ ├── (a=8, N=1, Q_v=0.56, best=0.56, ubc=1.66)
│ ├── (a=12, N=2, Q_v=0.87, best=0.89, ubc=1.65)
│ │ └── (a=8, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=19, N=2, Q_v=0.82, best=0.91, ubc=1.59)
│ │ └── (a=8, N=1, Q_v=0.73, best=0.73, ubc=1.32)
│ ├── (a=24, N=2, Q_v=0.66, best=0.71, ubc=1.44)
│ │ └── (a=8, N=1, Q_v=0.71, best=0.71, ubc=1.30)
│ └── (a=30, N=1, Q_v=0.62, best=0.62, ubc=1.71)
├── (a=12, N=10, Q_v=0.73, best=0.93, ubc=1.18)
│ ├── (a=0, N=2, Q_v=0.76, best=0.82, ubc=1.52)
│ │ └── (a=7, N=1, Q_v=0.82, best=0.82, ubc=1.41)
│ ├── (a=7, N=1, Q_v=0.64, best=0.64, ubc=1.71)
│ ├── (a=13, N=2, Q_v=0.86, best=0.93, ubc=1.62)
│ │ └── (a=7, N=1, Q_v=0.93, best=0.93, ubc=1.52)
│ ├── (a=19, N=1, Q_v=0.55, best=0.55, ubc=1.62)
│ ├── (a=24, N=1, Q_v=0.55, best=0.55, ubc=1.62)
│ └── (a=30, N=2, Q_v=0.84, best=0.89, ubc=1.59)
│ └── (a=24, N=1, Q_v=0.78, best=0.78, ubc=1.37)
├── (a=19, N=9, Q_v=0.70, best=0.89, ubc=1.17)
│ ├── (a=0, N=1, Q_v=0.76, best=0.76, ubc=1.81)
│ ├── (a=7, N=1, Q_v=0.45, best=0.45, ubc=1.50)
│ ├── (a=12, N=2, Q_v=0.81, best=0.89, ubc=1.55)
│ │ └── (a=24, N=1, Q_v=0.73, best=0.73, ubc=1.32)
│ ├── (a=20, N=1, Q_v=0.49, best=0.49, ubc=1.54)
│ ├── (a=24, N=1, Q_v=0.58, best=0.58, ubc=1.63)
│ └── (a=30, N=2, Q_v=0.76, best=0.89, ubc=1.50)
│ └── (a=31, N=1, Q_v=0.64, best=0.64, ubc=1.22)
├── (a=24, N=5, Q_v=0.54, best=0.69, ubc=1.17)
│ ├── (a=0, N=1, Q_v=0.58, best=0.58, ubc=1.48)
│ ├── (a=7, N=1, Q_v=0.45, best=0.45, ubc=1.35)
│ ├── (a=12, N=1, Q_v=0.51, best=0.51, ubc=1.41)
│ └── (a=19, N=1, Q_v=0.47, best=0.47, ubc=1.37)
└── (a=30, N=8, Q_v=0.70, best=0.91, ubc=1.19)
├── (a=0, N=2, Q_v=0.76, best=0.91, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.62, best=0.62, ubc=1.21)
├── (a=7, N=1, Q_v=0.76, best=0.76, ubc=1.78)
├── (a=12, N=1, Q_v=0.62, best=0.62, ubc=1.64)
├── (a=19, N=1, Q_v=0.67, best=0.67, ubc=1.69)
├── (a=24, N=1, Q_v=0.76, best=0.76, ubc=1.78)
└── (a=31, N=1, Q_v=0.49, best=0.49, ubc=1.51)
[16:52:33] INFO selected action 7 after 50 simulations.
INFO current action list: [18, 6, 7]
(N=50, Q_v=0.73, best=0.95)
├── (a=0, N=6, Q_v=0.67, best=0.85, ubc=1.24)
│ ├── (a=1, N=1, Q_v=0.82, best=0.82, ubc=1.76)
│ ├── (a=8, N=1, Q_v=0.56, best=0.56, ubc=1.51)
│ ├── (a=12, N=1, Q_v=0.85, best=0.85, ubc=1.80)
│ ├── (a=19, N=1, Q_v=0.58, best=0.58, ubc=1.53)
│ └── (a=24, N=1, Q_v=0.45, best=0.45, ubc=1.40)
├── (a=8, N=8, Q_v=0.69, best=0.93, ubc=1.18)
│ ├── (a=0, N=1, Q_v=0.60, best=0.60, ubc=1.62)
│ ├── (a=9, N=1, Q_v=0.55, best=0.55, ubc=1.56)
│ ├── (a=12, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=19, N=2, Q_v=0.65, best=0.93, ubc=1.37)
│ │ └── (a=30, N=1, Q_v=0.36, best=0.36, ubc=0.95)
│ ├── (a=24, N=1, Q_v=0.55, best=0.55, ubc=1.56)
│ └── (a=30, N=1, Q_v=0.76, best=0.76, ubc=1.78)
├── (a=12, N=13, Q_v=0.84, best=0.95, ubc=1.22)
│ ├── (a=0, N=2, Q_v=0.91, best=0.93, ubc=1.71)
│ │ └── (a=24, N=1, Q_v=0.93, best=0.93, ubc=1.52)
│ ├── (a=8, N=2, Q_v=0.81, best=0.89, ubc=1.61)
│ │ └── (a=24, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=13, N=2, Q_v=0.87, best=0.95, ubc=1.67)
│ │ └── (a=30, N=1, Q_v=0.80, best=0.80, ubc=1.39)
│ ├── (a=19, N=2, Q_v=0.64, best=0.67, ubc=1.44)
│ │ └── (a=20, N=1, Q_v=0.67, best=0.67, ubc=1.26)
│ ├── (a=24, N=2, Q_v=0.89, best=0.89, ubc=1.69)
│ │ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=30, N=2, Q_v=0.89, best=0.91, ubc=1.69)
│ └── (a=13, N=1, Q_v=0.87, best=0.87, ubc=1.46)
├── (a=19, N=9, Q_v=0.77, best=0.93, ubc=1.24)
│ ├── (a=0, N=1, Q_v=0.80, best=0.80, ubc=1.85)
│ ├── (a=8, N=1, Q_v=0.60, best=0.60, ubc=1.65)
│ ├── (a=12, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=8, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=20, N=2, Q_v=0.83, best=0.93, ubc=1.57)
│ │ └── (a=21, N=1, Q_v=0.73, best=0.73, ubc=1.32)
│ ├── (a=24, N=1, Q_v=0.36, best=0.36, ubc=1.41)
│ └── (a=30, N=1, Q_v=0.87, best=0.87, ubc=1.92)
├── (a=24, N=5, Q_v=0.57, best=0.73, ubc=1.19)
│ ├── (a=0, N=1, Q_v=0.64, best=0.64, ubc=1.53)
│ ├── (a=8, N=1, Q_v=0.69, best=0.69, ubc=1.59)
│ ├── (a=12, N=1, Q_v=0.22, best=0.22, ubc=1.12)
│ └── (a=25, N=1, Q_v=0.56, best=0.56, ubc=1.46)
└── (a=30, N=8, Q_v=0.75, best=0.89, ubc=1.24)
├── (a=0, N=1, Q_v=0.64, best=0.64, ubc=1.66)
├── (a=8, N=1, Q_v=0.84, best=0.84, ubc=1.86)
├── (a=12, N=2, Q_v=0.89, best=0.89, ubc=1.61)
│ └── (a=8, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=19, N=1, Q_v=0.53, best=0.53, ubc=1.55)
├── (a=24, N=1, Q_v=0.51, best=0.51, ubc=1.53)
└── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.91)
INFO selected action 12 after 50 simulations.
INFO current action list: [18, 6, 7, 12]
(N=50, Q_v=0.79, best=0.95)
├── (a=0, N=8, Q_v=0.79, best=0.87, ubc=1.28)
│ ├── (a=1, N=1, Q_v=0.84, best=0.84, ubc=1.86)
│ ├── (a=8, N=1, Q_v=0.78, best=0.78, ubc=1.80)
│ ├── (a=13, N=2, Q_v=0.83, best=0.87, ubc=1.55)
│ │ └── (a=19, N=1, Q_v=0.78, best=0.78, ubc=1.37)
│ ├── (a=19, N=1, Q_v=0.87, best=0.87, ubc=1.89)
│ ├── (a=24, N=1, Q_v=0.76, best=0.76, ubc=1.78)
│ └── (a=30, N=1, Q_v=0.87, best=0.87, ubc=1.89)
├── (a=8, N=10, Q_v=0.83, best=0.95, ubc=1.27)
│ ├── (a=0, N=1, Q_v=0.73, best=0.73, ubc=1.80)
│ ├── (a=9, N=1, Q_v=0.76, best=0.76, ubc=1.84)
│ ├── (a=13, N=1, Q_v=0.78, best=0.78, ubc=1.85)
│ ├── (a=19, N=2, Q_v=0.93, best=0.95, ubc=1.69)
│ │ └── (a=20, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ ├── (a=24, N=2, Q_v=0.85, best=0.85, ubc=1.61)
│ │ └── (a=9, N=1, Q_v=0.85, best=0.85, ubc=1.44)
│ └── (a=30, N=2, Q_v=0.83, best=0.91, ubc=1.59)
│ └── (a=9, N=1, Q_v=0.75, best=0.75, ubc=1.33)
├── (a=13, N=8, Q_v=0.79, best=0.95, ubc=1.29)
│ ├── (a=0, N=1, Q_v=0.55, best=0.55, ubc=1.56)
│ ├── (a=8, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=14, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=19, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ ├── (a=24, N=2, Q_v=0.85, best=0.95, ubc=1.58)
│ │ └── (a=8, N=1, Q_v=0.76, best=0.76, ubc=1.35)
│ └── (a=30, N=1, Q_v=0.67, best=0.67, ubc=1.69)
├── (a=19, N=6, Q_v=0.72, best=0.91, ubc=1.29)
│ ├── (a=0, N=1, Q_v=0.53, best=0.53, ubc=1.47)
│ ├── (a=8, N=1, Q_v=0.75, best=0.75, ubc=1.69)
│ ├── (a=13, N=1, Q_v=0.45, best=0.45, ubc=1.40)
│ ├── (a=20, N=1, Q_v=0.91, best=0.91, ubc=1.86)
│ └── (a=24, N=1, Q_v=0.91, best=0.91, ubc=1.86)
├── (a=24, N=8, Q_v=0.80, best=0.91, ubc=1.29)
│ ├── (a=0, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ ├── (a=8, N=1, Q_v=0.65, best=0.65, ubc=1.67)
│ ├── (a=13, N=1, Q_v=0.76, best=0.76, ubc=1.78)
│ ├── (a=19, N=1, Q_v=0.69, best=0.69, ubc=1.71)
│ ├── (a=25, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ └── (a=30, N=1, Q_v=0.80, best=0.80, ubc=1.82)
└── (a=30, N=9, Q_v=0.80, best=0.91, ubc=1.26)
├── (a=0, N=2, Q_v=0.80, best=0.85, ubc=1.54)
│ └── (a=19, N=1, Q_v=0.75, best=0.75, ubc=1.33)
├── (a=8, N=2, Q_v=0.83, best=0.91, ubc=1.57)
│ └── (a=13, N=1, Q_v=0.75, best=0.75, ubc=1.33)
├── (a=13, N=1, Q_v=0.80, best=0.80, ubc=1.85)
├── (a=19, N=1, Q_v=0.73, best=0.73, ubc=1.78)
├── (a=24, N=1, Q_v=0.85, best=0.85, ubc=1.90)
└── (a=31, N=1, Q_v=0.67, best=0.67, ubc=1.72)
[16:52:34] INFO selected action 8 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8]
(N=50, Q_v=0.83, best=0.95)
├── (a=0, N=6, Q_v=0.75, best=0.95, ubc=1.33)
│ ├── (a=1, N=1, Q_v=0.71, best=0.71, ubc=1.66)
│ ├── (a=9, N=1, Q_v=0.80, best=0.80, ubc=1.75)
│ ├── (a=13, N=1, Q_v=0.53, best=0.53, ubc=1.47)
│ ├── (a=19, N=1, Q_v=0.95, best=0.95, ubc=1.89)
│ └── (a=24, N=1, Q_v=0.69, best=0.69, ubc=1.64)
├── (a=9, N=9, Q_v=0.83, best=0.93, ubc=1.30)
│ ├── (a=0, N=1, Q_v=0.58, best=0.58, ubc=1.63)
│ ├── (a=10, N=2, Q_v=0.83, best=0.91, ubc=1.57)
│ │ └── (a=24, N=1, Q_v=0.75, best=0.75, ubc=1.33)
│ ├── (a=13, N=1, Q_v=0.85, best=0.85, ubc=1.90)
│ ├── (a=19, N=2, Q_v=0.91, best=0.93, ubc=1.65)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=24, N=1, Q_v=0.91, best=0.91, ubc=1.96)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=13, N=7, Q_v=0.79, best=0.89, ubc=1.32)
│ ├── (a=0, N=1, Q_v=0.75, best=0.75, ubc=1.73)
│ ├── (a=9, N=1, Q_v=0.58, best=0.58, ubc=1.57)
│ ├── (a=14, N=1, Q_v=0.85, best=0.85, ubc=1.84)
│ ├── (a=19, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=24, N=1, Q_v=0.75, best=0.75, ubc=1.73)
│ └── (a=30, N=1, Q_v=0.85, best=0.85, ubc=1.84)
├── (a=19, N=12, Q_v=0.92, best=0.95, ubc=1.32)
│ ├── (a=0, N=2, Q_v=0.93, best=0.95, ubc=1.72)
│ │ └── (a=13, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ ├── (a=9, N=2, Q_v=0.92, best=0.95, ubc=1.71)
│ │ └── (a=30, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ ├── (a=13, N=2, Q_v=0.94, best=0.95, ubc=1.72)
│ │ └── (a=14, N=1, Q_v=0.93, best=0.93, ubc=1.52)
│ ├── (a=20, N=2, Q_v=0.91, best=0.91, ubc=1.70)
│ │ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=24, N=1, Q_v=0.89, best=0.89, ubc=2.01)
│ └── (a=30, N=2, Q_v=0.94, best=0.95, ubc=1.72)
│ └── (a=20, N=1, Q_v=0.95, best=0.95, ubc=1.53)
├── (a=24, N=8, Q_v=0.81, best=0.89, ubc=1.31)
│ ├── (a=0, N=1, Q_v=0.51, best=0.51, ubc=1.53)
│ ├── (a=9, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ ├── (a=13, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ ├── (a=19, N=1, Q_v=0.87, best=0.87, ubc=1.89)
│ ├── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ └── (a=30, N=2, Q_v=0.83, best=0.89, ubc=1.55)
│ └── (a=0, N=1, Q_v=0.76, best=0.76, ubc=1.35)
└── (a=30, N=7, Q_v=0.80, best=0.87, ubc=1.33)
├── (a=0, N=1, Q_v=0.76, best=0.76, ubc=1.75)
├── (a=9, N=1, Q_v=0.85, best=0.85, ubc=1.84)
├── (a=13, N=1, Q_v=0.75, best=0.75, ubc=1.73)
├── (a=19, N=1, Q_v=0.73, best=0.73, ubc=1.71)
├── (a=24, N=1, Q_v=0.76, best=0.76, ubc=1.75)
└── (a=31, N=1, Q_v=0.85, best=0.85, ubc=1.84)
[16:52:35] INFO selected action 19 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19]
(N=50, Q_v=0.83, best=0.95)
├── (a=0, N=6, Q_v=0.73, best=0.87, ubc=1.30)
│ ├── (a=1, N=1, Q_v=0.71, best=0.71, ubc=1.66)
│ ├── (a=9, N=1, Q_v=0.65, best=0.65, ubc=1.60)
│ ├── (a=13, N=1, Q_v=0.85, best=0.85, ubc=1.80)
│ ├── (a=20, N=1, Q_v=0.73, best=0.73, ubc=1.67)
│ └── (a=30, N=1, Q_v=0.87, best=0.87, ubc=1.82)
├── (a=9, N=7, Q_v=0.77, best=0.89, ubc=1.30)
│ ├── (a=0, N=1, Q_v=0.75, best=0.75, ubc=1.73)
│ ├── (a=10, N=1, Q_v=0.75, best=0.75, ubc=1.73)
│ ├── (a=13, N=1, Q_v=0.73, best=0.73, ubc=1.71)
│ ├── (a=20, N=1, Q_v=0.85, best=0.85, ubc=1.84)
│ ├── (a=24, N=1, Q_v=0.80, best=0.80, ubc=1.79)
│ └── (a=30, N=1, Q_v=0.64, best=0.64, ubc=1.62)
├── (a=13, N=8, Q_v=0.85, best=0.95, ubc=1.34)
│ ├── (a=0, N=1, Q_v=0.69, best=0.69, ubc=1.71)
│ ├── (a=9, N=1, Q_v=0.93, best=0.93, ubc=1.95)
│ ├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=20, N=2, Q_v=0.92, best=0.95, ubc=1.64)
│ │ └── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=24, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.93)
├── (a=20, N=9, Q_v=0.85, best=0.95, ubc=1.32)
│ ├── (a=0, N=2, Q_v=0.74, best=0.95, ubc=1.48)
│ │ └── (a=1, N=1, Q_v=0.53, best=0.53, ubc=1.12)
│ ├── (a=9, N=1, Q_v=0.91, best=0.91, ubc=1.96)
│ ├── (a=13, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=21, N=1, Q_v=0.91, best=0.91, ubc=1.96)
│ ├── (a=24, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=30, N=2, Q_v=0.84, best=0.95, ubc=1.58)
│ └── (a=24, N=1, Q_v=0.73, best=0.73, ubc=1.32)
├── (a=24, N=10, Q_v=0.88, best=0.91, ubc=1.32)
│ ├── (a=0, N=2, Q_v=0.86, best=0.89, ubc=1.62)
│ │ └── (a=9, N=1, Q_v=0.84, best=0.84, ubc=1.42)
│ ├── (a=9, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=13, N=1, Q_v=0.85, best=0.85, ubc=1.93)
│ ├── (a=20, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ │ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.93)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.96)
└── (a=30, N=9, Q_v=0.85, best=0.95, ubc=1.32)
├── (a=0, N=1, Q_v=0.84, best=0.84, ubc=1.88)
├── (a=9, N=1, Q_v=0.76, best=0.76, ubc=1.81)
├── (a=13, N=2, Q_v=0.88, best=0.91, ubc=1.62)
│ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
├── (a=20, N=2, Q_v=0.93, best=0.95, ubc=1.67)
│ └── (a=9, N=1, Q_v=0.95, best=0.95, ubc=1.53)
├── (a=24, N=1, Q_v=0.84, best=0.84, ubc=1.88)
└── (a=31, N=1, Q_v=0.75, best=0.75, ubc=1.79)
INFO selected action 24 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24]
(N=50, Q_v=0.84, best=0.95)
├── (a=0, N=7, Q_v=0.78, best=0.89, ubc=1.31)
│ ├── (a=1, N=1, Q_v=0.85, best=0.85, ubc=1.84)
│ ├── (a=9, N=1, Q_v=0.71, best=0.71, ubc=1.70)
│ ├── (a=13, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=20, N=1, Q_v=0.55, best=0.55, ubc=1.53)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ └── (a=30, N=1, Q_v=0.69, best=0.69, ubc=1.68)
├── (a=9, N=9, Q_v=0.86, best=0.91, ubc=1.33)
│ ├── (a=0, N=1, Q_v=0.75, best=0.75, ubc=1.79)
│ ├── (a=10, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=20, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=13, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=20, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=30, N=1, Q_v=0.85, best=0.85, ubc=1.90)
├── (a=13, N=7, Q_v=0.81, best=0.91, ubc=1.34)
│ ├── (a=0, N=1, Q_v=0.76, best=0.76, ubc=1.75)
│ ├── (a=9, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=14, N=1, Q_v=0.91, best=0.91, ubc=1.90)
│ ├── (a=20, N=1, Q_v=0.91, best=0.91, ubc=1.90)
│ ├── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.84)
│ └── (a=30, N=1, Q_v=0.75, best=0.75, ubc=1.73)
├── (a=20, N=10, Q_v=0.87, best=0.91, ubc=1.32)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=9, N=1, Q_v=0.85, best=0.85, ubc=1.93)
│ ├── (a=13, N=2, Q_v=0.88, best=0.91, ubc=1.64)
│ │ └── (a=9, N=1, Q_v=0.85, best=0.85, ubc=1.44)
│ ├── (a=21, N=1, Q_v=0.85, best=0.85, ubc=1.93)
│ ├── (a=25, N=2, Q_v=0.85, best=0.89, ubc=1.60)
│ │ └── (a=30, N=1, Q_v=0.80, best=0.80, ubc=1.39)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=25, N=8, Q_v=0.85, best=0.89, ubc=1.35)
│ ├── (a=0, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ ├── (a=9, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ ├── (a=13, N=1, Q_v=0.82, best=0.82, ubc=1.84)
│ ├── (a=20, N=2, Q_v=0.89, best=0.89, ubc=1.61)
│ │ └── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=26, N=1, Q_v=0.80, best=0.80, ubc=1.82)
│ └── (a=30, N=1, Q_v=0.85, best=0.85, ubc=1.87)
└── (a=30, N=8, Q_v=0.85, best=0.95, ubc=1.35)
├── (a=0, N=1, Q_v=0.73, best=0.73, ubc=1.75)
├── (a=9, N=1, Q_v=0.80, best=0.80, ubc=1.82)
├── (a=13, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=20, N=1, Q_v=0.85, best=0.85, ubc=1.87)
├── (a=25, N=2, Q_v=0.90, best=0.95, ubc=1.62)
│ └── (a=26, N=1, Q_v=0.85, best=0.85, ubc=1.44)
└── (a=31, N=1, Q_v=0.85, best=0.85, ubc=1.87)
[16:52:36] INFO selected action 20 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20]
(N=50, Q_v=0.83, best=0.91)
├── (a=0, N=9, Q_v=0.86, best=0.91, ubc=1.32)
│ ├── (a=1, N=2, Q_v=0.91, best=0.91, ubc=1.65)
│ │ └── (a=13, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=9, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=13, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=9, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=21, N=1, Q_v=0.91, best=0.91, ubc=1.96)
│ ├── (a=25, N=1, Q_v=0.58, best=0.58, ubc=1.63)
│ └── (a=30, N=1, Q_v=0.87, best=0.87, ubc=1.92)
├── (a=9, N=9, Q_v=0.87, best=0.91, ubc=1.33)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=1, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=10, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=13, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=21, N=1, Q_v=0.91, best=0.91, ubc=1.96)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.96)
├── (a=13, N=6, Q_v=0.75, best=0.89, ubc=1.32)
│ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.84)
│ ├── (a=9, N=1, Q_v=0.73, best=0.73, ubc=1.67)
│ ├── (a=14, N=1, Q_v=0.75, best=0.75, ubc=1.69)
│ ├── (a=21, N=1, Q_v=0.62, best=0.62, ubc=1.56)
│ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.84)
├── (a=21, N=8, Q_v=0.81, best=0.91, ubc=1.30)
│ ├── (a=0, N=2, Q_v=0.76, best=0.91, ubc=1.48)
│ │ └── (a=1, N=1, Q_v=0.62, best=0.62, ubc=1.21)
│ ├── (a=9, N=1, Q_v=0.80, best=0.80, ubc=1.82)
│ ├── (a=13, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=22, N=1, Q_v=0.58, best=0.58, ubc=1.60)
│ ├── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=25, N=8, Q_v=0.83, best=0.91, ubc=1.33)
│ ├── (a=0, N=1, Q_v=0.62, best=0.62, ubc=1.64)
│ ├── (a=9, N=2, Q_v=0.91, best=0.91, ubc=1.63)
│ │ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=13, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=21, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
└── (a=30, N=9, Q_v=0.86, best=0.91, ubc=1.32)
├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=9, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=13, N=2, Q_v=0.85, best=0.91, ubc=1.60)
│ └── (a=21, N=1, Q_v=0.80, best=0.80, ubc=1.39)
├── (a=21, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=25, N=1, Q_v=0.91, best=0.91, ubc=1.96)
└── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.94)
INFO selected action 9 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9]
(N=50, Q_v=0.85, best=0.91)
├── (a=0, N=6, Q_v=0.77, best=0.89, ubc=1.34)
│ ├── (a=1, N=1, Q_v=0.58, best=0.58, ubc=1.53)
│ ├── (a=10, N=1, Q_v=0.80, best=0.80, ubc=1.75)
│ ├── (a=13, N=1, Q_v=0.89, best=0.89, ubc=1.84)
│ ├── (a=21, N=1, Q_v=0.56, best=0.56, ubc=1.51)
│ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.84)
├── (a=10, N=9, Q_v=0.86, best=0.91, ubc=1.33)
│ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=13, N=2, Q_v=0.91, best=0.91, ubc=1.65)
│ │ └── (a=21, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=21, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=13, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=25, N=1, Q_v=0.91, best=0.91, ubc=1.96)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=13, N=10, Q_v=0.89, best=0.91, ubc=1.33)
│ ├── (a=0, N=2, Q_v=0.86, best=0.91, ubc=1.62)
│ │ └── (a=1, N=1, Q_v=0.82, best=0.82, ubc=1.41)
│ ├── (a=10, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=14, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ │ └── (a=21, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.96)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.96)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=21, N=7, Q_v=0.80, best=0.91, ubc=1.33)
│ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=10, N=1, Q_v=0.62, best=0.62, ubc=1.60)
│ ├── (a=13, N=1, Q_v=0.56, best=0.56, ubc=1.55)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=25, N=1, Q_v=0.91, best=0.91, ubc=1.90)
│ └── (a=30, N=1, Q_v=0.85, best=0.85, ubc=1.84)
├── (a=25, N=8, Q_v=0.85, best=0.91, ubc=1.35)
│ ├── (a=0, N=2, Q_v=0.85, best=0.91, ubc=1.58)
│ │ └── (a=30, N=1, Q_v=0.80, best=0.80, ubc=1.39)
│ ├── (a=10, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=13, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=21, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ ├── (a=26, N=1, Q_v=0.80, best=0.80, ubc=1.82)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
└── (a=30, N=9, Q_v=0.89, best=0.91, ubc=1.36)
├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ └── (a=10, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=10, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=13, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ └── (a=10, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.90)
└── (a=31, N=1, Q_v=0.85, best=0.85, ubc=1.90)
[16:52:37] INFO selected action 13 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13]
(N=50, Q_v=0.82, best=0.91)
├── (a=0, N=4, Q_v=0.62, best=0.80, ubc=1.32)
│ ├── (a=1, N=1, Q_v=0.55, best=0.55, ubc=1.38)
│ ├── (a=10, N=1, Q_v=0.51, best=0.51, ubc=1.34)
│ └── (a=21, N=1, Q_v=0.62, best=0.62, ubc=1.45)
├── (a=10, N=11, Q_v=0.89, best=0.89, ubc=1.31)
│ ├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.67)
│ │ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=11, N=2, Q_v=0.88, best=0.89, ubc=1.66)
│ │ └── (a=14, N=1, Q_v=0.87, best=0.87, ubc=1.46)
│ ├── (a=14, N=2, Q_v=0.89, best=0.89, ubc=1.67)
│ │ └── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=21, N=2, Q_v=0.88, best=0.89, ubc=1.66)
│ │ └── (a=14, N=1, Q_v=0.87, best=0.87, ubc=1.46)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.99)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.99)
├── (a=14, N=7, Q_v=0.78, best=0.91, ubc=1.31)
│ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=10, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=15, N=1, Q_v=0.55, best=0.55, ubc=1.53)
│ ├── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=25, N=1, Q_v=0.69, best=0.69, ubc=1.68)
│ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.90)
├── (a=21, N=10, Q_v=0.85, best=0.91, ubc=1.29)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=10, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=14, N=2, Q_v=0.84, best=0.89, ubc=1.59)
│ │ └── (a=10, N=1, Q_v=0.78, best=0.78, ubc=1.37)
│ ├── (a=22, N=1, Q_v=0.62, best=0.62, ubc=1.69)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.96)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=25, N=7, Q_v=0.76, best=0.89, ubc=1.29)
│ ├── (a=0, N=1, Q_v=0.62, best=0.62, ubc=1.60)
│ ├── (a=10, N=1, Q_v=0.56, best=0.56, ubc=1.55)
│ ├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=26, N=1, Q_v=0.56, best=0.56, ubc=1.55)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.88)
└── (a=30, N=10, Q_v=0.87, best=0.91, ubc=1.31)
├── (a=0, N=1, Q_v=0.78, best=0.78, ubc=1.85)
├── (a=10, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=14, N=1, Q_v=0.80, best=0.80, ubc=1.87)
├── (a=21, N=2, Q_v=0.87, best=0.89, ubc=1.63)
│ └── (a=10, N=1, Q_v=0.85, best=0.85, ubc=1.44)
├── (a=25, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
└── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
[16:52:38] INFO selected action 10 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10]
(N=50, Q_v=0.88, best=0.95)
├── (a=0, N=8, Q_v=0.87, best=0.95, ubc=1.36)
│ ├── (a=1, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=11, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=14, N=2, Q_v=0.92, best=0.95, ubc=1.64)
│ │ └── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=21, N=1, Q_v=0.62, best=0.62, ubc=1.64)
│ ├── (a=25, N=1, Q_v=0.87, best=0.87, ubc=1.89)
│ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.93)
├── (a=11, N=8, Q_v=0.86, best=0.89, ubc=1.36)
│ ├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.61)
│ │ └── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=14, N=2, Q_v=0.82, best=0.89, ubc=1.54)
│ │ └── (a=21, N=1, Q_v=0.75, best=0.75, ubc=1.33)
│ ├── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=14, N=8, Q_v=0.89, best=0.91, ubc=1.39)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=15, N=1, Q_v=0.91, best=0.91, ubc=1.93)
│ ├── (a=21, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.87)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=21, N=9, Q_v=0.90, best=0.91, ubc=1.37)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=11, N=2, Q_v=0.91, best=0.91, ubc=1.65)
│ │ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=25, N=8, Q_v=0.88, best=0.91, ubc=1.38)
│ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=14, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=21, N=1, Q_v=0.80, best=0.80, ubc=1.82)
│ ├── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
└── (a=30, N=8, Q_v=0.88, best=0.91, ubc=1.38)
├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=14, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ └── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=21, N=1, Q_v=0.80, best=0.80, ubc=1.82)
├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
└── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.91)
[16:52:39] INFO selected action 21 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21]
(N=50, Q_v=0.85, best=0.91)
├── (a=0, N=7, Q_v=0.79, best=0.89, ubc=1.32)
│ ├── (a=1, N=1, Q_v=0.80, best=0.80, ubc=1.79)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.88)
│ ├── (a=25, N=1, Q_v=0.75, best=0.75, ubc=1.73)
│ └── (a=30, N=1, Q_v=0.80, best=0.80, ubc=1.79)
├── (a=11, N=9, Q_v=0.87, best=0.91, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.83, best=0.89, ubc=1.57)
│ │ └── (a=30, N=1, Q_v=0.76, best=0.76, ubc=1.35)
│ ├── (a=14, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=30, N=1, Q_v=0.85, best=0.85, ubc=1.90)
├── (a=14, N=8, Q_v=0.84, best=0.91, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=11, N=1, Q_v=0.58, best=0.58, ubc=1.60)
│ ├── (a=15, N=1, Q_v=0.76, best=0.76, ubc=1.78)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=30, N=1, Q_v=0.91, best=0.91, ubc=1.93)
├── (a=22, N=8, Q_v=0.85, best=0.91, ubc=1.35)
│ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=14, N=2, Q_v=0.73, best=0.91, ubc=1.45)
│ │ └── (a=0, N=1, Q_v=0.55, best=0.55, ubc=1.13)
│ ├── (a=23, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=25, N=8, Q_v=0.84, best=0.91, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.85, best=0.89, ubc=1.57)
│ │ └── (a=1, N=1, Q_v=0.80, best=0.80, ubc=1.39)
│ ├── (a=11, N=1, Q_v=0.58, best=0.58, ubc=1.60)
│ ├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=30, N=1, Q_v=0.89, best=0.89, ubc=1.91)
└── (a=30, N=9, Q_v=0.88, best=0.91, ubc=1.35)
├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ └── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=25, N=2, Q_v=0.91, best=0.91, ubc=1.65)
│ └── (a=14, N=1, Q_v=0.91, best=0.91, ubc=1.50)
└── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.94)
INFO selected action 30 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30]
(N=50, Q_v=0.89, best=0.93)
├── (a=0, N=9, Q_v=0.89, best=0.93, ubc=1.36)
│ ├── (a=1, N=2, Q_v=0.87, best=0.89, ubc=1.61)
│ │ └── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.44)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=14, N=2, Q_v=0.91, best=0.93, ubc=1.65)
│ │ └── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.94)
├── (a=11, N=8, Q_v=0.90, best=0.91, ubc=1.39)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=14, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=14, N=8, Q_v=0.90, best=0.91, ubc=1.39)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.93)
├── (a=22, N=8, Q_v=0.90, best=0.91, ubc=1.39)
│ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=23, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=31, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ └── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=25, N=8, Q_v=0.89, best=0.91, ubc=1.39)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ │ └── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=11, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ ├── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.91)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.91)
└── (a=31, N=8, Q_v=0.87, best=0.91, ubc=1.37)
├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=32, N=1, Q_v=0.80, best=0.80, ubc=1.82)
├── (a=11, N=2, Q_v=0.90, best=0.91, ubc=1.62)
│ └── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.91)
├── (a=22, N=1, Q_v=0.80, best=0.80, ubc=1.82)
└── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.91)
[16:52:40] INFO selected action 11 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11]
(N=50, Q_v=0.89, best=0.95)
├── (a=0, N=10, Q_v=0.89, best=0.91, ubc=1.34)
│ ├── (a=1, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ │ └── (a=2, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=14, N=1, Q_v=0.85, best=0.85, ubc=1.93)
│ ├── (a=22, N=2, Q_v=0.89, best=0.91, ubc=1.65)
│ │ └── (a=23, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=25, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ └── (a=32, N=1, Q_v=0.91, best=0.91, ubc=1.50)
├── (a=14, N=10, Q_v=0.90, best=0.95, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=25, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=15, N=2, Q_v=0.92, best=0.95, ubc=1.68)
│ │ └── (a=16, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=23, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=25, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=22, N=10, Q_v=0.90, best=0.91, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=14, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ │ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=23, N=1, Q_v=0.87, best=0.87, ubc=1.95)
│ ├── (a=25, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=23, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=25, N=10, Q_v=0.89, best=0.89, ubc=1.33)
│ ├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=14, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=26, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=14, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.85, best=0.85, ubc=1.93)
└── (a=31, N=9, Q_v=0.88, best=0.95, ubc=1.35)
├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ └── (a=32, N=1, Q_v=0.91, best=0.91, ubc=1.50)
├── (a=32, N=1, Q_v=0.80, best=0.80, ubc=1.85)
├── (a=14, N=2, Q_v=0.92, best=0.95, ubc=1.66)
│ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=22, N=1, Q_v=0.80, best=0.80, ubc=1.85)
└── (a=25, N=2, Q_v=0.90, best=0.91, ubc=1.64)
└── (a=32, N=1, Q_v=0.89, best=0.89, ubc=1.48)
[16:52:41] INFO selected action 14 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14]
(N=50, Q_v=0.88, best=0.91)
├── (a=0, N=9, Q_v=0.87, best=0.91, ubc=1.33)
│ ├── (a=1, N=1, Q_v=0.82, best=0.82, ubc=1.87)
│ ├── (a=15, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=25, N=1, Q_v=0.85, best=0.85, ubc=1.90)
│ └── (a=31, N=2, Q_v=0.84, best=0.89, ubc=1.58)
│ └── (a=25, N=1, Q_v=0.78, best=0.78, ubc=1.37)
├── (a=15, N=10, Q_v=0.87, best=0.91, ubc=1.32)
│ ├── (a=0, N=2, Q_v=0.85, best=0.89, ubc=1.60)
│ │ └── (a=31, N=1, Q_v=0.80, best=0.80, ubc=1.39)
│ ├── (a=16, N=1, Q_v=0.80, best=0.80, ubc=1.87)
│ ├── (a=22, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=23, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=25, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ └── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=22, N=10, Q_v=0.89, best=0.91, ubc=1.33)
│ ├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=15, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=23, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=25, N=1, Q_v=0.89, best=0.89, ubc=1.96)
│ └── (a=31, N=2, Q_v=0.85, best=0.91, ubc=1.61)
│ └── (a=15, N=1, Q_v=0.80, best=0.80, ubc=1.39)
├── (a=25, N=10, Q_v=0.89, best=0.89, ubc=1.33)
│ ├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=15, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=26, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
└── (a=31, N=10, Q_v=0.88, best=0.91, ubc=1.33)
├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ └── (a=32, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=32, N=1, Q_v=0.78, best=0.78, ubc=1.85)
├── (a=15, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ └── (a=16, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ └── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.48)
└── (a=25, N=2, Q_v=0.90, best=0.91, ubc=1.66)
└── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.50)
[16:52:42] INFO selected action 25 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25]
(N=50, Q_v=0.90, best=0.95)
├── (a=0, N=10, Q_v=0.89, best=0.91, ubc=1.34)
│ ├── (a=1, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=15, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=1, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.96)
│ └── (a=31, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ └── (a=1, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=15, N=10, Q_v=0.91, best=0.95, ubc=1.35)
│ ├── (a=0, N=2, Q_v=0.92, best=0.95, ubc=1.68)
│ │ └── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=16, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ │ └── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=22, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=16, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.96)
│ └── (a=31, N=2, Q_v=0.92, best=0.93, ubc=1.68)
│ └── (a=16, N=1, Q_v=0.93, best=0.93, ubc=1.52)
├── (a=22, N=10, Q_v=0.89, best=0.91, ubc=1.33)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=23, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=15, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=23, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=26, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=27, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=26, N=10, Q_v=0.89, best=0.91, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=15, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=27, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=28, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
└── (a=31, N=9, Q_v=0.89, best=0.91, ubc=1.36)
├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=32, N=1, Q_v=0.85, best=0.85, ubc=1.90)
├── (a=15, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.94)
└── (a=26, N=2, Q_v=0.90, best=0.91, ubc=1.64)
└── (a=15, N=1, Q_v=0.89, best=0.89, ubc=1.48)
[16:52:43] INFO selected action 15 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15]
(N=50, Q_v=0.90, best=0.95)
├── (a=0, N=9, Q_v=0.89, best=0.91, ubc=1.36)
│ ├── (a=1, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=16, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=31, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=16, N=10, Q_v=0.91, best=0.95, ubc=1.35)
│ ├── (a=0, N=2, Q_v=0.92, best=0.95, ubc=1.68)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ ├── (a=17, N=2, Q_v=0.95, best=0.95, ubc=1.70)
│ │ └── (a=26, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ ├── (a=22, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ │ └── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=26, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=22, N=10, Q_v=0.89, best=0.91, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=1, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=16, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=23, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=26, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=23, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=26, N=10, Q_v=0.88, best=0.91, ubc=1.32)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=16, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=27, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=22, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=27, N=2, Q_v=0.79, best=0.89, ubc=1.55)
│ │ └── (a=31, N=1, Q_v=0.69, best=0.69, ubc=1.28)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
└── (a=31, N=10, Q_v=0.90, best=0.95, ubc=1.34)
├── (a=0, N=2, Q_v=0.91, best=0.93, ubc=1.67)
│ └── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=32, N=1, Q_v=0.80, best=0.80, ubc=1.87)
├── (a=16, N=2, Q_v=0.93, best=0.95, ubc=1.69)
│ └── (a=22, N=1, Q_v=0.91, best=0.91, ubc=1.50)
├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
└── (a=26, N=2, Q_v=0.91, best=0.91, ubc=1.67)
└── (a=16, N=1, Q_v=0.91, best=0.91, ubc=1.50)
INFO selected action 16 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16]
(N=50, Q_v=0.90, best=0.95)
├── (a=0, N=9, Q_v=0.89, best=0.95, ubc=1.36)
│ ├── (a=1, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=2, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=17, N=2, Q_v=0.93, best=0.95, ubc=1.67)
│ │ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=22, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ ├── (a=26, N=1, Q_v=0.85, best=0.85, ubc=1.90)
│ └── (a=31, N=2, Q_v=0.85, best=0.91, ubc=1.60)
│ └── (a=17, N=1, Q_v=0.80, best=0.80, ubc=1.39)
├── (a=17, N=11, Q_v=0.92, best=0.95, ubc=1.34)
│ ├── (a=0, N=3, Q_v=0.92, best=0.95, ubc=1.55)
│ │ ├── (a=1, N=1, Q_v=0.91, best=0.91, ubc=1.65)
│ │ └── (a=22, N=1, Q_v=0.91, best=0.91, ubc=1.65)
│ ├── (a=26, N=3, Q_v=0.95, best=0.95, ubc=1.58)
│ │ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=22, N=2, Q_v=0.91, best=0.91, ubc=1.68)
│ │ └── (a=26, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ └── (a=31, N=2, Q_v=0.89, best=0.89, ubc=1.67)
│ └── (a=32, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=22, N=10, Q_v=0.90, best=0.91, ubc=1.34)
│ ├── (a=0, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=1, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=17, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ │ └── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=23, N=2, Q_v=0.90, best=0.91, ubc=1.66)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=26, N=2, Q_v=0.89, best=0.89, ubc=1.65)
│ │ └── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.96)
├── (a=26, N=9, Q_v=0.89, best=0.91, ubc=1.36)
│ ├── (a=0, N=2, Q_v=0.90, best=0.91, ubc=1.64)
│ │ └── (a=27, N=1, Q_v=0.91, best=0.91, ubc=1.50)
│ ├── (a=17, N=2, Q_v=0.88, best=0.91, ubc=1.62)
│ │ └── (a=31, N=1, Q_v=0.85, best=0.85, ubc=1.44)
│ ├── (a=22, N=2, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=23, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ ├── (a=27, N=1, Q_v=0.89, best=0.89, ubc=1.94)
│ └── (a=31, N=1, Q_v=0.89, best=0.89, ubc=1.94)
└── (a=31, N=10, Q_v=0.90, best=0.95, ubc=1.34)
├── (a=0, N=2, Q_v=0.90, best=0.93, ubc=1.66)
│ └── (a=17, N=1, Q_v=0.87, best=0.87, ubc=1.46)
├── (a=32, N=2, Q_v=0.92, best=0.95, ubc=1.68)
│ └── (a=33, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=17, N=1, Q_v=0.84, best=0.84, ubc=1.91)
├── (a=22, N=2, Q_v=0.91, best=0.91, ubc=1.67)
│ └── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.50)
└── (a=26, N=2, Q_v=0.91, best=0.91, ubc=1.67)
└── (a=17, N=1, Q_v=0.91, best=0.91, ubc=1.50)
[16:52:44] INFO selected action 17 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17]
(N=50, Q_v=0.92, best=0.95)
├── (a=0, N=12, Q_v=0.92, best=0.95, ubc=1.32)
│ ├── (a=1, N=3, Q_v=0.92, best=0.93, ubc=1.56)
│ │ ├── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=26, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=26, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=22, N=3, Q_v=0.90, best=0.91, ubc=1.55)
│ │ ├── (a=1, N=1, Q_v=0.91, best=0.91, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.63)
│ └── (a=31, N=2, Q_v=0.90, best=0.91, ubc=1.69)
│ └── (a=32, N=1, Q_v=0.91, best=0.91, ubc=1.50)
├── (a=26, N=14, Q_v=0.94, best=0.95, ubc=1.31)
│ ├── (a=0, N=3, Q_v=0.93, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=27, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=27, N=3, Q_v=0.92, best=0.95, ubc=1.58)
│ │ ├── (a=0, N=1, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=22, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=22, N=4, Q_v=0.95, best=0.95, ubc=1.52)
│ │ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ ├── (a=27, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.61)
│ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=22, N=11, Q_v=0.89, best=0.91, ubc=1.31)
│ ├── (a=0, N=3, Q_v=0.90, best=0.91, ubc=1.54)
│ │ ├── (a=1, N=1, Q_v=0.91, best=0.91, ubc=1.65)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.63)
│ ├── (a=26, N=3, Q_v=0.90, best=0.91, ubc=1.54)
│ │ ├── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.65)
│ │ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.65)
│ ├── (a=31, N=2, Q_v=0.89, best=0.89, ubc=1.67)
│ │ └── (a=26, N=1, Q_v=0.89, best=0.89, ubc=1.48)
│ └── (a=23, N=2, Q_v=0.85, best=0.91, ubc=1.63)
│ └── (a=31, N=1, Q_v=0.91, best=0.91, ubc=1.50)
└── (a=31, N=12, Q_v=0.92, best=0.95, ubc=1.32)
├── (a=0, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=26, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=26, N=3, Q_v=0.93, best=0.95, ubc=1.57)
│ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=27, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=32, N=2, Q_v=0.86, best=0.95, ubc=1.65)
│ └── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=22, N=3, Q_v=0.91, best=0.91, ubc=1.55)
├── (a=0, N=1, Q_v=0.91, best=0.91, ubc=1.65)
└── (a=23, N=1, Q_v=0.91, best=0.91, ubc=1.65)
[16:52:45] INFO selected action 26 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26]
(N=50, Q_v=0.94, best=0.95)
├── (a=0, N=13, Q_v=0.94, best=0.95, ubc=1.33)
│ ├── (a=1, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=27, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=22, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=27, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=27, N=12, Q_v=0.94, best=0.95, ubc=1.34)
│ ├── (a=0, N=3, Q_v=0.92, best=0.95, ubc=1.56)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=28, N=1, Q_v=0.89, best=0.89, ubc=1.63)
│ ├── (a=28, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=0, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=22, N=2, Q_v=0.94, best=0.95, ubc=1.72)
│ │ └── (a=0, N=1, Q_v=0.93, best=0.93, ubc=1.52)
│ └── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=22, N=12, Q_v=0.94, best=0.95, ubc=1.35)
│ ├── (a=0, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=27, N=2, Q_v=0.94, best=0.95, ubc=1.72)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ ├── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ ├── (a=0, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=31, N=12, Q_v=0.93, best=0.95, ubc=1.33)
├── (a=0, N=2, Q_v=0.84, best=0.95, ubc=1.62)
│ └── (a=32, N=1, Q_v=0.73, best=0.73, ubc=1.32)
├── (a=32, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=27, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=22, N=3, Q_v=0.95, best=0.95, ubc=1.59)
├── (a=0, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=27, N=1, Q_v=0.95, best=0.95, ubc=1.69)
[16:52:46] INFO selected action 0 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0]
(N=50, Q_v=0.94, best=0.95)
├── (a=1, N=12, Q_v=0.93, best=0.95, ubc=1.34)
│ ├── (a=2, N=3, Q_v=0.93, best=0.95, ubc=1.58)
│ │ ├── (a=27, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=3, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=27, N=2, Q_v=0.93, best=0.93, ubc=1.72)
│ │ └── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.52)
│ ├── (a=22, N=3, Q_v=0.93, best=0.95, ubc=1.58)
│ │ ├── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=27, N=13, Q_v=0.94, best=0.95, ubc=1.33)
│ ├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ │ ├── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=22, N=3, Q_v=0.93, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=31, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ └── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=22, N=12, Q_v=0.94, best=0.95, ubc=1.34)
│ ├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=27, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.94, best=0.95, ubc=1.72)
│ └── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=31, N=12, Q_v=0.94, best=0.95, ubc=1.34)
├── (a=32, N=2, Q_v=0.92, best=0.95, ubc=1.71)
│ └── (a=33, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=27, N=1, Q_v=0.93, best=0.93, ubc=1.67)
├── (a=27, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ ├── (a=32, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=22, N=3, Q_v=0.95, best=0.95, ubc=1.59)
├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
[16:52:47] INFO selected action 27 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27]
(N=50, Q_v=0.93, best=0.95)
├── (a=1, N=11, Q_v=0.92, best=0.95, ubc=1.34)
│ ├── (a=2, N=3, Q_v=0.87, best=0.95, ubc=1.50)
│ │ ├── (a=3, N=1, Q_v=0.73, best=0.73, ubc=1.47)
│ │ └── (a=31, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=28, N=3, Q_v=0.94, best=0.95, ubc=1.57)
│ │ ├── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=22, N=2, Q_v=0.94, best=0.95, ubc=1.71)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ └── (a=31, N=2, Q_v=0.94, best=0.95, ubc=1.71)
│ └── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.52)
├── (a=28, N=12, Q_v=0.93, best=0.95, ubc=1.33)
│ ├── (a=1, N=3, Q_v=0.93, best=0.93, ubc=1.57)
│ │ ├── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=22, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=29, N=2, Q_v=0.93, best=0.93, ubc=1.72)
│ │ └── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.52)
│ ├── (a=22, N=3, Q_v=0.93, best=0.95, ubc=1.58)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=31, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=22, N=13, Q_v=0.94, best=0.95, ubc=1.32)
│ ├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ │ ├── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=31, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=31, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ │ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ └── (a=23, N=3, Q_v=0.93, best=0.93, ubc=1.58)
│ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ └── (a=31, N=1, Q_v=0.93, best=0.93, ubc=1.67)
└── (a=31, N=13, Q_v=0.94, best=0.95, ubc=1.33)
├── (a=32, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
├── (a=28, N=3, Q_v=0.93, best=0.95, ubc=1.58)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=1, N=1, Q_v=0.89, best=0.89, ubc=1.63)
└── (a=22, N=3, Q_v=0.95, best=0.95, ubc=1.60)
├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
INFO selected action 31 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31]
(N=50, Q_v=0.93, best=0.95)
├── (a=32, N=12, Q_v=0.93, best=0.95, ubc=1.34)
│ ├── (a=1, N=3, Q_v=0.93, best=0.95, ubc=1.57)
│ │ ├── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=22, N=3, Q_v=0.93, best=0.95, ubc=1.58)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=33, N=2, Q_v=0.92, best=0.95, ubc=1.71)
│ └── (a=34, N=1, Q_v=0.89, best=0.89, ubc=1.48)
├── (a=1, N=12, Q_v=0.93, best=0.95, ubc=1.34)
│ ├── (a=32, N=3, Q_v=0.93, best=0.95, ubc=1.57)
│ │ ├── (a=33, N=1, Q_v=0.89, best=0.89, ubc=1.63)
│ │ └── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=2, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=3, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ ├── (a=28, N=2, Q_v=0.92, best=0.95, ubc=1.71)
│ │ └── (a=22, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ └── (a=22, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=28, N=12, Q_v=0.92, best=0.95, ubc=1.33)
│ ├── (a=32, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=1, N=3, Q_v=0.93, best=0.95, ubc=1.57)
│ │ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=2, N=1, Q_v=0.89, best=0.89, ubc=1.63)
│ ├── (a=29, N=3, Q_v=0.87, best=0.95, ubc=1.52)
│ │ ├── (a=32, N=1, Q_v=0.73, best=0.73, ubc=1.47)
│ │ └── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=22, N=2, Q_v=0.95, best=0.95, ubc=1.73)
│ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=22, N=13, Q_v=0.94, best=0.95, ubc=1.33)
├── (a=32, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=1, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=28, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=1, Q_v=0.93, best=0.93, ubc=1.67)
└── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.60)
├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
[16:52:48] INFO selected action 22 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22]
(N=50, Q_v=0.94, best=0.95)
├── (a=32, N=13, Q_v=0.94, best=0.95, ubc=1.33)
│ ├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.59)
│ │ ├── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=33, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=1, N=12, Q_v=0.94, best=0.95, ubc=1.34)
│ ├── (a=32, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=2, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.93, best=0.93, ubc=1.72)
│ └── (a=32, N=1, Q_v=0.93, best=0.93, ubc=1.52)
├── (a=28, N=12, Q_v=0.94, best=0.95, ubc=1.34)
│ ├── (a=32, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=1, N=2, Q_v=0.93, best=0.93, ubc=1.72)
│ │ └── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.52)
│ ├── (a=29, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ └── (a=23, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ ├── (a=32, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ └── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=23, N=12, Q_v=0.94, best=0.95, ubc=1.35)
├── (a=32, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ ├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
└── (a=28, N=4, Q_v=0.95, best=0.95, ubc=1.50)
├── (a=32, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.78)
└── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.78)
[16:52:49] INFO selected action 32 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32]
(N=50, Q_v=0.94, best=0.95)
├── (a=1, N=12, Q_v=0.94, best=0.95, ubc=1.34)
│ ├── (a=33, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=2, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.93, best=0.93, ubc=1.72)
│ └── (a=28, N=1, Q_v=0.93, best=0.93, ubc=1.52)
├── (a=28, N=12, Q_v=0.94, best=0.95, ubc=1.35)
│ ├── (a=1, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=33, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=1, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=29, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.94, best=0.95, ubc=1.72)
│ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.53)
├── (a=33, N=13, Q_v=0.95, best=0.95, ubc=1.33)
│ ├── (a=1, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=34, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=23, N=12, Q_v=0.94, best=0.95, ubc=1.35)
├── (a=1, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ ├── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
├── (a=28, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=33, N=1, Q_v=0.95, best=0.95, ubc=1.78)
└── (a=33, N=4, Q_v=0.95, best=0.95, ubc=1.50)
├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.78)
└── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
[16:52:50] INFO selected action 33 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33]
(N=50, Q_v=0.94, best=0.95)
├── (a=1, N=12, Q_v=0.94, best=0.95, ubc=1.35)
│ ├── (a=2, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.94, best=0.95, ubc=1.58)
│ │ ├── (a=2, N=1, Q_v=0.93, best=0.93, ubc=1.67)
│ │ └── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=34, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.73)
│ └── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.53)
├── (a=34, N=13, Q_v=0.95, best=0.95, ubc=1.33)
│ ├── (a=1, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=35, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=28, N=12, Q_v=0.94, best=0.95, ubc=1.35)
│ ├── (a=1, N=2, Q_v=0.94, best=0.95, ubc=1.72)
│ │ └── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.53)
│ ├── (a=34, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=29, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=23, N=12, Q_v=0.95, best=0.95, ubc=1.35)
├── (a=1, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=34, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
└── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.59)
├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=34, N=1, Q_v=0.95, best=0.95, ubc=1.69)
[16:52:51] INFO selected action 34 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34]
(N=50, Q_v=0.95, best=0.95)
├── (a=1, N=13, Q_v=0.95, best=0.95, ubc=1.33)
│ ├── (a=2, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=35, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=35, N=12, Q_v=0.95, best=0.95, ubc=1.35)
│ ├── (a=1, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ ├── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=28, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ ├── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=28, N=12, Q_v=0.95, best=0.95, ubc=1.35)
│ ├── (a=1, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=35, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=29, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.73)
│ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=23, N=12, Q_v=0.95, best=0.95, ubc=1.35)
├── (a=1, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=35, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=1, N=2, Q_v=0.95, best=0.95, ubc=1.53)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
└── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.59)
├── (a=1, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
INFO selected action 1 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1]
(N=50, Q_v=0.95, best=0.95)
├── (a=2, N=13, Q_v=0.95, best=0.95, ubc=1.33)
│ ├── (a=35, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=3, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=4, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.60)
│ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=35, N=12, Q_v=0.95, best=0.95, ubc=1.35)
│ ├── (a=2, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ │ ├── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ ├── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=28, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ ├── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
├── (a=28, N=12, Q_v=0.95, best=0.95, ubc=1.35)
│ ├── (a=2, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=35, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=29, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.73)
│ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=23, N=12, Q_v=0.95, best=0.95, ubc=1.35)
├── (a=2, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=35, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=2, N=2, Q_v=0.95, best=0.95, ubc=1.53)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
└── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.59)
├── (a=2, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
[16:52:52] INFO selected action 2 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2]
(N=50, Q_v=0.95, best=0.95)
├── (a=35, N=13, Q_v=0.95, best=0.95, ubc=1.33)
│ ├── (a=3, N=4, Q_v=0.95, best=0.95, ubc=1.51)
│ │ ├── (a=4, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ ├── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=28, N=4, Q_v=0.95, best=0.95, ubc=1.51)
│ │ ├── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ ├── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=23, N=4, Q_v=0.95, best=0.95, ubc=1.51)
│ ├── (a=3, N=2, Q_v=0.95, best=0.95, ubc=1.53)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=3, N=12, Q_v=0.95, best=0.95, ubc=1.35)
│ ├── (a=35, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=4, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=4, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.73)
│ └── (a=4, N=1, Q_v=0.95, best=0.95, ubc=1.53)
├── (a=28, N=12, Q_v=0.95, best=0.95, ubc=1.35)
│ ├── (a=35, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=3, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=4, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ ├── (a=29, N=3, Q_v=0.95, best=0.95, ubc=1.59)
│ │ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ │ └── (a=3, N=1, Q_v=0.95, best=0.95, ubc=1.69)
│ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.73)
│ └── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=23, N=12, Q_v=0.95, best=0.95, ubc=1.35)
├── (a=35, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=3, N=2, Q_v=0.95, best=0.95, ubc=1.53)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
├── (a=3, N=4, Q_v=0.95, best=0.95, ubc=1.50)
│ ├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ ├── (a=4, N=1, Q_v=0.95, best=0.95, ubc=1.78)
│ └── (a=28, N=1, Q_v=0.95, best=0.95, ubc=1.78)
└── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.59)
├── (a=35, N=1, Q_v=0.95, best=0.95, ubc=1.69)
└── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.69)
[16:52:53] INFO selected action 35 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35]
(N=50, Q_v=0.95, best=0.95)
├── (a=3, N=17, Q_v=0.95, best=0.95, ubc=1.28)
│ ├── (a=4, N=6, Q_v=0.95, best=0.95, ubc=1.43)
│ │ ├── (a=28, N=2, Q_v=0.95, best=0.95, ubc=1.61)
│ │ ├── (a=5, N=2, Q_v=0.95, best=0.95, ubc=1.61)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.89)
│ ├── (a=28, N=5, Q_v=0.95, best=0.95, ubc=1.48)
│ │ ├── (a=4, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ │ ├── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.84)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.84)
│ └── (a=23, N=5, Q_v=0.95, best=0.95, ubc=1.48)
│ ├── (a=4, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=28, N=2, Q_v=0.95, best=0.95, ubc=1.58)
├── (a=28, N=16, Q_v=0.95, best=0.95, ubc=1.30)
│ ├── (a=3, N=5, Q_v=0.95, best=0.95, ubc=1.47)
│ │ ├── (a=4, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ │ ├── (a=29, N=1, Q_v=0.95, best=0.95, ubc=1.84)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.84)
│ ├── (a=29, N=5, Q_v=0.95, best=0.95, ubc=1.47)
│ │ ├── (a=3, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ │ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=23, N=5, Q_v=0.95, best=0.95, ubc=1.47)
│ ├── (a=3, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=29, N=2, Q_v=0.95, best=0.95, ubc=1.58)
└── (a=23, N=16, Q_v=0.95, best=0.95, ubc=1.30)
├── (a=3, N=8, Q_v=0.95, best=0.95, ubc=1.36)
│ ├── (a=4, N=4, Q_v=0.95, best=0.95, ubc=1.46)
│ └── (a=28, N=3, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=28, N=7, Q_v=0.95, best=0.95, ubc=1.39)
├── (a=3, N=3, Q_v=0.95, best=0.95, ubc=1.51)
└── (a=29, N=3, Q_v=0.95, best=0.95, ubc=1.51)
[16:52:54] INFO selected action 3 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35, 3]
(N=50, Q_v=0.95, best=0.95)
├── (a=4, N=17, Q_v=0.95, best=0.95, ubc=1.28)
│ ├── (a=28, N=6, Q_v=0.95, best=0.95, ubc=1.43)
│ │ ├── (a=29, N=2, Q_v=0.95, best=0.95, ubc=1.61)
│ │ ├── (a=5, N=2, Q_v=0.95, best=0.95, ubc=1.61)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.89)
│ ├── (a=5, N=5, Q_v=0.95, best=0.95, ubc=1.48)
│ │ ├── (a=28, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ │ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=23, N=5, Q_v=0.95, best=0.95, ubc=1.48)
│ ├── (a=28, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=5, N=2, Q_v=0.95, best=0.95, ubc=1.58)
├── (a=28, N=16, Q_v=0.95, best=0.95, ubc=1.30)
│ ├── (a=4, N=5, Q_v=0.95, best=0.95, ubc=1.47)
│ │ ├── (a=29, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ │ ├── (a=5, N=1, Q_v=0.95, best=0.95, ubc=1.84)
│ │ └── (a=23, N=1, Q_v=0.95, best=0.95, ubc=1.84)
│ ├── (a=29, N=5, Q_v=0.95, best=0.95, ubc=1.47)
│ │ ├── (a=4, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ │ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=23, N=5, Q_v=0.95, best=0.95, ubc=1.47)
│ ├── (a=4, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=29, N=2, Q_v=0.95, best=0.95, ubc=1.58)
└── (a=23, N=16, Q_v=0.95, best=0.95, ubc=1.30)
├── (a=4, N=8, Q_v=0.95, best=0.95, ubc=1.36)
│ ├── (a=28, N=4, Q_v=0.95, best=0.95, ubc=1.46)
│ └── (a=5, N=3, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=28, N=7, Q_v=0.95, best=0.95, ubc=1.39)
├── (a=4, N=3, Q_v=0.95, best=0.95, ubc=1.51)
└── (a=29, N=3, Q_v=0.95, best=0.95, ubc=1.51)
[16:52:55] INFO selected action 4 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35, 3, 4]
(N=50, Q_v=0.95, best=0.95)
├── (a=28, N=17, Q_v=0.95, best=0.95, ubc=1.28)
│ ├── (a=29, N=6, Q_v=0.95, best=0.95, ubc=1.43)
│ │ ├── (a=5, N=3, Q_v=0.95, best=0.95, ubc=1.49)
│ │ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.61)
│ ├── (a=5, N=5, Q_v=0.95, best=0.95, ubc=1.48)
│ │ ├── (a=29, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ │ └── (a=23, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=23, N=5, Q_v=0.95, best=0.95, ubc=1.48)
│ ├── (a=29, N=2, Q_v=0.95, best=0.95, ubc=1.58)
│ └── (a=5, N=2, Q_v=0.95, best=0.95, ubc=1.58)
├── (a=5, N=16, Q_v=0.95, best=0.95, ubc=1.30)
│ ├── (a=28, N=8, Q_v=0.95, best=0.95, ubc=1.36)
│ │ ├── (a=29, N=4, Q_v=0.95, best=0.95, ubc=1.46)
│ │ └── (a=23, N=3, Q_v=0.95, best=0.95, ubc=1.53)
│ └── (a=23, N=7, Q_v=0.95, best=0.95, ubc=1.39)
│ └── (a=28, N=6, Q_v=0.95, best=0.95, ubc=1.35)
└── (a=23, N=16, Q_v=0.95, best=0.95, ubc=1.30)
├── (a=28, N=8, Q_v=0.95, best=0.95, ubc=1.36)
│ ├── (a=29, N=4, Q_v=0.95, best=0.95, ubc=1.46)
│ └── (a=5, N=3, Q_v=0.95, best=0.95, ubc=1.53)
└── (a=5, N=7, Q_v=0.95, best=0.95, ubc=1.39)
└── (a=28, N=6, Q_v=0.95, best=0.95, ubc=1.35)
INFO selected action 28 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35, 3, 4, 28]
(N=50, Q_v=0.95, best=0.95)
├── (a=29, N=17, Q_v=0.95, best=0.95, ubc=1.28)
│ ├── (a=5, N=8, Q_v=0.95, best=0.95, ubc=1.37)
│ │ └── (a=23, N=7, Q_v=0.95, best=0.95, ubc=1.33)
│ └── (a=23, N=8, Q_v=0.95, best=0.95, ubc=1.37)
│ └── (a=5, N=7, Q_v=0.95, best=0.95, ubc=1.33)
├── (a=5, N=16, Q_v=0.95, best=0.95, ubc=1.30)
│ ├── (a=29, N=8, Q_v=0.95, best=0.95, ubc=1.36)
│ │ └── (a=23, N=7, Q_v=0.95, best=0.95, ubc=1.33)
│ └── (a=23, N=7, Q_v=0.95, best=0.95, ubc=1.39)
│ └── (a=29, N=6, Q_v=0.95, best=0.95, ubc=1.35)
└── (a=23, N=16, Q_v=0.95, best=0.95, ubc=1.30)
├── (a=29, N=8, Q_v=0.95, best=0.95, ubc=1.36)
│ └── (a=5, N=7, Q_v=0.95, best=0.95, ubc=1.33)
└── (a=5, N=7, Q_v=0.95, best=0.95, ubc=1.39)
└── (a=29, N=6, Q_v=0.95, best=0.95, ubc=1.35)
[16:52:56] INFO selected action 29 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35, 3, 4, 28, 29]
(N=50, Q_v=0.95, best=0.95)
├── (a=5, N=25, Q_v=0.95, best=0.95, ubc=1.23)
│ └── (a=23, N=24, Q_v=0.95, best=0.95, ubc=1.20)
└── (a=23, N=24, Q_v=0.95, best=0.95, ubc=1.23)
└── (a=5, N=23, Q_v=0.95, best=0.95, ubc=1.21)
INFO selected action 5 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35, 3, 4, 28, 29, 5]
(N=50, Q_v=0.95, best=0.95)
└── (a=23, N=49, Q_v=0.95, best=0.95, ubc=1.15)
[16:52:57] INFO selected action 23 after 50 simulations.
INFO current action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35, 3, 4, 28, 29, 5, 23]
INFO Final action list: [18, 6, 7, 12, 8, 19, 24, 20, 9, 13, 10, 21, 30, 11, 14, 25, 15, 16, 17, 26, 0, 27, 31, 22, 32, 33, 34, 1, 2, 35, 3, 4, 28, 29, 5, 23]
Job 0 ●-●-●-●-●-● Machine 0 █
Job 1 ●-●-●-●-●-● Machine 1 █
Job 2 ●-●-●-●-●-● Machine 2 █
Job 3 ●-●-●-●-●-● Machine 3 █
Job 4 ●-●-●-●-●-● Machine 4 █
Job 5 ●-●-●-●-●-● Machine 5 █
╔═══════════════════════════════════════════════════════╗
Job 0 ║ █ ███ █████████████ ██ ██████║ Machine 0 █
Job 1 ║ ████████████████████████████████████████████ ║ Machine 1 █
Job 2 ║██████████████████████████ ██████ ║ Machine 2 █
Job 3 ║██████████ ███████ ████████████████ ║ Machine 3 █
Job 4 ║ ███████████ █████████ ███ █ ║ Machine 4 █
Job 5 ║ ███████████████████████ █████ ║ Machine 5 █
╚╦════╤════╤════╤════╤════╦════╤════╤════╤════╤════╦════╝
0.0 26.8 53.6
makespan: 58