geek-ai/MAgent
A Platform for Many-Agent Reinforcement Learning
This research platform helps AI researchers study artificial collective intelligence, specifically how hundreds to millions of AI agents learn and interact within an environment. Researchers provide agent rules or deep learning models and define an environment, then observe emergent behaviors and learning patterns from the collective. It's designed for academics and practitioners exploring the dynamics of large-scale multi-agent systems.
1,758 stars. No commits in the last 6 months.
Use this if you are an AI researcher developing and testing reinforcement learning algorithms that involve hundreds or millions of interacting agents.
Not ideal if you need a pre-built, production-ready solution for managing real-world multi-agent systems, or if your research focuses on single-agent or very few-agent reinforcement learning.
Stars
1,758
Forks
333
Language
Python
License
MIT
Category
Last pushed
Oct 22, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/geek-ai/MAgent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
gtri/scrimmage
Multi-Agent Robotics Simulator