Robust MARL algos

(Currently for SustainGym.)

Basic usage

$ python3 trainer_susgym.py

$ python3 trainer_susgym.py --good-policy rmaddpg --train-summer-pct 0.75 --eval-summer-pct 0. --eval-num-runs 10

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
__pycache__		__pycache__
multiagent		multiagent
results/simple_spread_False		results/simple_spread_False
robust_envs		robust_envs
tensorboard-logs/simple_spread_False		tensorboard-logs/simple_spread_False
.DS_Store		.DS_Store
.gitattributes		.gitattributes
README.md		README.md
__init__.py		__init__.py
agents.py		agents.py
distributions.py		distributions.py
memory.py		memory.py
models.py		models.py
trainer.py		trainer.py
trainer_marllib.py		trainer_marllib.py
trainer_susgym.py		trainer_susgym.py