geek-ai/MAgent
A Platform for Many-Agent Reinforcement Learning
Supports large-scale multi-agent scenarios (hundreds to millions of agents) through a C++ engine with WebSocket-based communication, enabling research beyond single or few-agent setups. Built on parameter-sharing DQN, DRQN, and A2C baselines implemented in TensorFlow and MXNet, with environment simulators for competitive (battle, pursuit) and cooperative (gathering) tasks on grid worlds.
1,758 stars. No commits in the last 6 months.
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
facebookresearch/BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL...
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
utiasDSL/gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
koulanurag/ma-gym
A collection of multi agent environments based on OpenAI gym.