{
"cells": [
{
"cell_type": "markdown",
"id": "cdf95c4d",
"metadata": {},
"source": [
"# FrozenLake 6x6"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "7c1861a0",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-04T15:47:16.929681Z",
"start_time": "2025-03-04T15:47:16.819817Z"
}
},
"outputs": [],
"source": [
"import gymnasium as gym"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5e2b1e8c",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-04T15:47:16.960091Z",
"start_time": "2025-03-04T15:47:16.930773Z"
}
},
"outputs": [],
"source": [
"from gymcts.gymcts_agent import GymctsAgent\n",
"from gymcts.gymcts_deepcopy_wrapper import DeepCopyMCTSGymEnvWrapper"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "939b8006",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-04T15:47:16.962718Z",
"start_time": "2025-03-04T15:47:16.960880Z"
}
},
"outputs": [],
"source": [
"from gymcts.logger import log"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "1139a220",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-04T15:47:16.965129Z",
"start_time": "2025-03-04T15:47:16.963303Z"
}
},
"outputs": [],
"source": [
"log.setLevel(20)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "503eb755",
"metadata": {
"ExecuteTime": {
"end_time": "2025-03-04T15:47:31.112138Z",
"start_time": "2025-03-04T15:47:16.966014Z"
}
},
"outputs": [
{
"data": {
"text/html": [
"[16:47:17] INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:17]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:18] INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:18]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:19] INFO selected action 0 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:19]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m0\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 0 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m0\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:20] INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:20]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:21] INFO selected action 2 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:21]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m2\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 0 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m0\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:22] INFO selected action 2 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:22]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m2\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:23] INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:23]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:24] INFO selected action 3 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:24]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m3\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:25] INFO selected action 0 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:25]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m0\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:26] INFO selected action 3 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:26]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m3\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 2 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m2\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:27] INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:27]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:28] INFO selected action 2 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:28]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m2\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:29] INFO selected action 0 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:29]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m0\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:30] INFO selected action 3 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:30]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m3\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0, 3] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 2 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m2\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0, 3, 2] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0, 3, 2, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 0 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m0\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0, 3, 2, 1, 0] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO selected action 2 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m2\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0, 3, 2, 1, 0, 2] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"[16:47:31] INFO selected action 1 after 200 simulations. \n",
"\n"
],
"text/plain": [
"\u001B[2;36m[16:47:31]\u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m selected action \u001B[1;36m1\u001B[0m after \u001B[1;36m200\u001B[0m simulations. \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO current action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0, 3, 2, 1, 0, 2, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m current action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
" INFO Final action list: [1, 1, 0, 0, 1, 2, 0, 2, 1, 3, 1, 0, 3, 2, 1, 2, 1, 0, 3, 2, 1, 0, 2, 1] \n",
"\n"
],
"text/plain": [
"\u001B[2;36m \u001B[0m\u001B[2;36m \u001B[0m\u001B[34mINFO \u001B[0m Final action list: \u001B[1m[\u001B[0m\u001B[1;36m1\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m3\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m, \u001B[1;36m0\u001B[0m, \u001B[1;36m2\u001B[0m, \u001B[1;36m1\u001B[0m\u001B[1m]\u001B[0m \n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001B[41mS\u001B[0mFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"S\u001B[41mF\u001B[0mFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"\u001B[41mS\u001B[0mFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Left)\n",
"\u001B[41mS\u001B[0mFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Left)\n",
"\u001B[41mS\u001B[0mFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"\u001B[41mS\u001B[0mFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Right)\n",
"S\u001B[41mF\u001B[0mFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Left)\n",
"\u001B[41mS\u001B[0mFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Right)\n",
"S\u001B[41mF\u001B[0mFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"SFFFFF\n",
"F\u001B[41mF\u001B[0mFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Up)\n",
"SFFFFF\n",
"\u001B[41mF\u001B[0mFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"SFFFFF\n",
"\u001B[41mF\u001B[0mFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Left)\n",
"SFFFFF\n",
"\u001B[41mF\u001B[0mFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Up)\n",
"\u001B[41mS\u001B[0mFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Right)\n",
"SFFFFF\n",
"\u001B[41mF\u001B[0mFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"SFFFFF\n",
"\u001B[41mF\u001B[0mFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Right)\n",
"SFFFFF\n",
"F\u001B[41mF\u001B[0mFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"SFFFFF\n",
"FFFFFF\n",
"F\u001B[41mF\u001B[0mFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Left)\n",
"SFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"F\u001B[41mF\u001B[0mFFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Up)\n",
"SFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FF\u001B[41mF\u001B[0mFFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Right)\n",
"SFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFF\u001B[41mF\u001B[0mFH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"SFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFF\u001B[41mF\u001B[0mH\n",
"FHFFFF\n",
"FFFFFG\n",
"\n",
" (Left)\n",
"SFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFF\u001B[41mF\u001B[0mF\n",
"FFFFFG\n",
"\n",
" (Right)\n",
"SFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFF\u001B[41mF\u001B[0m\n",
"FFFFFG\n",
"\n",
" (Down)\n",
"SFFFFF\n",
"FFFFFF\n",
"FFFHFF\n",
"FFFFFH\n",
"FHFFFF\n",
"FFFFF\u001B[41mG\u001B[0m\n"
]
}
],
"source": [
"if __name__ == '__main__':\n",
" log.debug(\"Starting example\")\n",
"\n",
" # 0. create the environment\n",
" custom_map = [\n",
" \"SFFFFF\",\n",
" \"FFFFFF\",\n",
" \"FFFHFF\",\n",
" \"FFFFFH\",\n",
" \"FHFFFF\",\n",
" \"FFFFFG\"\n",
" ]\n",
" env = gym.make(\n",
" 'FrozenLake-v1',\n",
" desc=custom_map,\n",
" map_name=None,\n",
" is_slippery=True,\n",
" render_mode=\"ansi\"\n",
" )\n",
" env.reset()\n",
"\n",
" # 1. wrap the environment with the naive wrapper or a custom gymcts wrapper\n",
" env = DeepCopyMCTSGymEnvWrapper(env)\n",
"\n",
" # 2. create the agent\n",
" agent = GymctsAgent(env=env, clear_mcts_tree_after_step=False)\n",
"\n",
" # 3. solve the environment\n",
" actions = agent.solve(num_simulations_per_step=200)\n",
"\n",
" # 4. render the environment solution in the terminal\n",
" print(env.render())\n",
" for a in actions:\n",
" obs, rew, term, trun, info = env.step(a)\n",
" print(env.render())"
]
}
],
"metadata": {
"jupytext": {
"cell_metadata_filter": "-all",
"main_language": "python",
"notebook_metadata_filter": "-all"
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}