marlbenchmark/on-policy
This is the official implementation of Multi-Agent PPO (MAPPO).
Implements centralized training with decentralized execution (CTDE) using shared policy networks across agents, with support for diverse benchmarks including SMAC v2, Google Research Football, Hanabi, and MPE environments. The codebase provides environment wrappers, rollout runners, and pre-tuned hyperparameter scripts for each scenario, emphasizing reproducibility through detailed configuration management and documented training curves from the original paper.
1,914 stars. No commits in the last 6 months.
Stars
1,914
Forks
371
Language
Python
License
MIT
Category
Last pushed
Jul 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/marlbenchmark/on-policy"
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...
datamllab/rlcard
Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.
Toni-SM/skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with...
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.