koulanurag/ma-gym

A collection of multi agent environments based on OpenAI gym.

58
/ 100
Established

This project provides pre-built simulated environments where multiple independent entities (agents) interact, similar to scenarios in games like Checkers or real-world problems like traffic management. It takes an agent's actions as input and provides new observations and rewards, allowing you to train and test how these agents learn to behave. Researchers and engineers working on multi-agent reinforcement learning problems would use this.

629 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need ready-to-use, standardized environments to develop and evaluate multi-agent learning algorithms.

Not ideal if you are looking for a tool to deploy trained agents directly into real-world applications without further development.

multi-agent-systems reinforcement-learning-research game-AI-development simulated-environments autonomous-system-testing
Stale 6m
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 23 / 25

How are scores calculated?

Stars

629

Forks

114

Language

Python

License

Apache-2.0

Last pushed

Jul 07, 2024

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/koulanurag/ma-gym"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.