mctspy

Name	mctspy JSON
Version	0.1.1 JSON
	download
home_page	https://github.com/int8/monte-carlo-tree-search
Summary	Python implementation of monte carlo tree search for 2 players zero-sum game
upload_time	2019-07-16 13:55:55
maintainer
docs_url	None
author	Kamil Czarnogórski
requires_python	>=3.5.7
license
keywords	mcts monte carlo tree search
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            ## mctspy : python implementation of Monte Carlo Tree Search algorithm


Basic python implementation of [Monte Carlo Tree Search](https://int8.io/monte-carlo-tree-search-beginners-guide) (MCTS) intended to run on small game trees. 


### Installation

```
pip3 install mctspy
``` 

### Running tic-tac-toe example 

to run tic-tac-toe example:

```python

import numpy as np
from mctspy.tree.nodes import TwoPlayersGameMonteCarloTreeSearchNode
from mctspy.tree.search import MonteCarloTreeSearch
from mctspy.games.examples.tictactoe import TicTacToeGameState

state = np.zeros((3,3))
initial_board_state = TicTacToeGameState(state = state, next_to_move=1)

root = TwoPlayersGameMonteCarloTreeSearchNode(state = initial_board_state)
mcts = MonteCarloTreeSearch(root)
best_node = mcts.best_action(10000)

```


### Running MCTS for your own 2 players zero-sum game 

If you want to apply MCTS for your own game, its state implementation should derive from  
`mmctspy.games.common.TwoPlayersGameState` 

(lookup `mctspy.games.examples.tictactoe.TicTacToeGameState` for inspiration)


            

Raw data

            {
    "_id": null,
    "home_page": "https://github.com/int8/monte-carlo-tree-search",
    "name": "mctspy",
    "maintainer": "",
    "docs_url": null,
    "requires_python": ">=3.5.7",
    "maintainer_email": "",
    "keywords": "mcts monte carlo tree search",
    "author": "Kamil Czarnog\u00f3rski",
    "author_email": "",
    "download_url": "https://files.pythonhosted.org/packages/b3/48/cefb7f055e308c9ce63dbe079c23d6195be3040d42c3596ee515d66b02b6/mctspy-0.1.1.tar.gz",
    "platform": "",
    "description": "## mctspy : python implementation of Monte Carlo Tree Search algorithm\n\n\nBasic python implementation of [Monte Carlo Tree Search](https://int8.io/monte-carlo-tree-search-beginners-guide) (MCTS) intended to run on small game trees. \n\n\n### Installation\n\n```\npip3 install mctspy\n``` \n\n### Running tic-tac-toe example \n\nto run tic-tac-toe example:\n\n```python\n\nimport numpy as np\nfrom mctspy.tree.nodes import TwoPlayersGameMonteCarloTreeSearchNode\nfrom mctspy.tree.search import MonteCarloTreeSearch\nfrom mctspy.games.examples.tictactoe import TicTacToeGameState\n\nstate = np.zeros((3,3))\ninitial_board_state = TicTacToeGameState(state = state, next_to_move=1)\n\nroot = TwoPlayersGameMonteCarloTreeSearchNode(state = initial_board_state)\nmcts = MonteCarloTreeSearch(root)\nbest_node = mcts.best_action(10000)\n\n```\n\n\n### Running MCTS for your own 2 players zero-sum game \n\nIf you want to apply MCTS for your own game, its state implementation should derive from  \n`mmctspy.games.common.TwoPlayersGameState` \n\n(lookup `mctspy.games.examples.tictactoe.TicTacToeGameState` for inspiration)\n\n",
    "bugtrack_url": null,
    "license": "",
    "summary": "Python implementation of monte carlo tree search for 2 players zero-sum game",
    "version": "0.1.1",
    "split_keywords": [
        "mcts",
        "monte",
        "carlo",
        "tree",
        "search"
    ],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "md5": "eeed96f969d129c50d354253d8242f3c",
                "sha256": "fc7a87aa7654971ede89b63a58d2ed3171a498937d38bd7b53b79f4dea880354"
            },
            "downloads": -1,
            "filename": "mctspy-0.1.1-py3-none-any.whl",
            "has_sig": false,
            "md5_digest": "eeed96f969d129c50d354253d8242f3c",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": ">=3.5.7",
            "size": 6336,
            "upload_time": "2019-07-16T13:55:54",
            "upload_time_iso_8601": "2019-07-16T13:55:54.292767Z",
            "url": "https://files.pythonhosted.org/packages/93/25/fb9812b54a0c7c6db86fa4ca89d1eb0db9f30d7242832bdb91dde950d818/mctspy-0.1.1-py3-none-any.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": "",
            "digests": {
                "md5": "42d49ca857cf4dd39c5aa70cc2b018aa",
                "sha256": "52d16193bdadeaca144bf28047367c13e8940a45d758a3a9c96c78d3b7226dfa"
            },
            "downloads": -1,
            "filename": "mctspy-0.1.1.tar.gz",
            "has_sig": false,
            "md5_digest": "42d49ca857cf4dd39c5aa70cc2b018aa",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": ">=3.5.7",
            "size": 4064,
            "upload_time": "2019-07-16T13:55:55",
            "upload_time_iso_8601": "2019-07-16T13:55:55.833626Z",
            "url": "https://files.pythonhosted.org/packages/b3/48/cefb7f055e308c9ce63dbe079c23d6195be3040d42c3596ee515d66b02b6/mctspy-0.1.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2019-07-16 13:55:55",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "github_user": "int8",
    "github_project": "monte-carlo-tree-search",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": false,
    "lcname": "mctspy"
}