implementation of MADDPG using PyTorch and multiagent-particle-envs
training and evaluation is simple and straightforward, take simple_spread for example:
python main.py simple_adversary # training
python evaluate.py simple_adversary # evaluationmore details about arguments can be found in main.py, evaluate.py
or simply run python main.py --help, python evaluate.py --help
| environment name | training result | evaluation result |
|---|---|---|
| simple_adversary |  |
 |
| simple_tag |  |
 |
- implementation of openai
- implementation of Git-123-Hub