ArnaudFickinger/gym-multigrid

Lightweight multi-agent gridworld Gym environment

47
/ 100
Emerging

This project helps researchers and developers design and test artificial intelligence agents that need to collaborate or compete in a confined, grid-like space. You can define the environment's layout, rules, and objects, and then simulate how agents interact with each other and their surroundings. It's used by AI researchers and machine learning engineers working on multi-agent reinforcement learning.

213 stars. No commits in the last 6 months.

Use this if you are developing or evaluating AI agents that need to learn cooperative or competitive strategies in a simple, customizable gridworld.

Not ideal if you need a high-fidelity 3D simulation, realistic physics, or extremely complex environments for your multi-agent AI research.

multi-agent-systems reinforcement-learning AI-simulation robotics-planning agent-behavior-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

213

Forks

42

Language

Python

License

Apache-2.0

Last pushed

Sep 21, 2023

Commits (30d)

0

Get this data via API

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

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