Skip to main content

OpenAI Gym-compatible implementation of the game CoMaze to benchmark AI on Zero-Shot Emergent Coordination and Communication.

Project description

CoMaze Gym

An OpenAI Gym-compatible implementation of the zero-shot coordination and communication benchmark game CoMaze.

Description

For an exhaustive description of the game, please refer to this page.

Usage

gym must be installed. An Kuhn's poker environment can be created via running inside a python interpreter:

>>> import gym
>>> import comaze_gym
>>> env = gym.make('CoMaze-7x7-Sparse-v0')

Installation

Installing via pip

This package is available in PyPi as comaze-gym

pip install comaze-gym

Installing via cloning this repository

git clone https://www.github.com/Near32/comaze-gym
cd comaze-gym
pip install -e .

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

comaze_gym-0.0.1.tar.gz (11.6 kB view hashes)

Uploaded Source

Built Distribution

comaze_gym-0.0.1-py3-none-any.whl (12.6 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page