https://github.com/michaelmior/lasvegas

A neural network for learning to play the Las Vegas dice game :game_die:
https://github.com/michaelmior/lasvegas

board-game neural-network

Last synced: about 1 month ago
JSON representation

A neural network for learning to play the Las Vegas dice game :game_die:

• Host: GitHub
• URL: https://github.com/michaelmior/lasvegas
• Owner: michaelmior
• Created: 2017-12-08T04:04:30.000Z (about 7 years ago)
• Default Branch: main
• Last Pushed: 2023-07-16T11:11:51.000Z (over 1 year ago)
• Last Synced: 2024-11-08T09:47:03.586Z (3 months ago)
• Topics: board-game, neural-network
• Language: Python
• Homepage:
• Size: 24.4 KB
• Stars: 0
• Watchers: 3
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Las Vegas AI

This repo implements an AI for the dice game [Las Vegas](https://boardgamegeek.com/boardgame/117959/las-vegas) based on [deep-Q learning with experience replay](https://arxiv.org/abs/1312.5602).

Currently this has only been tested with Python 3.6 using the Theano backend of Keras.

## Installation

    export PYTHONPATH=.

    pip install -r requirements.txt

## Getting started

The repository contains two scripts [`bin/lasvegas-train`](bin/lasvegas-train) and [`bin/lasvegas-eval`](bin/lasvegas-eval).

Both can be run with `--help` to list the available options.

By default running `lasvegas-train` will train a neural network in a game against random players and save the model to `model.h5`.

Models can be evaluated by running `lasvegas-eval -m model.h5` to produce the average score in games against random players.