This implementation of MADDPG is recommended for research purposes only. If you want to actually learn something, use parameter sharing.
-This was forked from wsjeons's original repo due to lack of maintenance
-
The codes in OpenAI/MADDPG were refactored in RLlib, and test results are given in
./plots.- It was tested on 7 scenarios of OpenAI/Multi-Agent Particle Environment (MPE).
simple,simple_adversary,simple_crypto,simple_push,simple_speaker_listener,simple_spread,simple_tag- RLlib MADDPG shows the similar performance as OpenAI MADDPG on 7 scenarios except
simple_crypto.
- RLlib MADDPG shows the similar performance as OpenAI MADDPG on 7 scenarios except
- Hyperparameters were set to follow the original hyperparameter setting in OpenAI/MADDPG.
- It was tested on 7 scenarios of OpenAI/Multi-Agent Particle Environment (MPE).
-
Empirically, removing lz4 makes running much faster. I guess this is due to the small-size observation in MPE.
- OpenAI/MADDPG
- OpenAI/Multi-Agent Particle Environment
- wsjeon/Multi-Agent Particle Environment
- It includes the minor change for MPE to work with recent OpenAI Gym.
- wsjeon/Multi-Agent Particle Environment