matteokarldonati / Counterfactual-Multi-Agent-Policy-Gradients Public

Notifications You must be signed in to change notification settings
Fork 11
Star 57

PyTorch implementation of Foerster, Jakob N., et al. "Counterfactual multi-agent policy gradients."

57 stars 11 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
doc		doc
.gitignore		.gitignore
COMA.ipynb		COMA.ipynb
COMA.py		COMA.py
README.md		README.md
training_loop.py		training_loop.py

Repository files navigation

Pytorch implementation of Counterfactual Multi Agent Policy Gradients

Paper: https://arxiv.org/abs/1705.08926

Environment

The model was tested on the ma-gym Switch2-v0 environment (https://github.com/koulanurag/ma-gym/wiki/Environments#Switch)

Results

Policy:

Learning Curve:

About

PyTorch implementation of Foerster, Jakob N., et al. "Counterfactual multi-agent policy gradients."

reinforcement-learning deep-reinforcement-learning multi-agent-reinforcement-learning

Report repository

Releases

No releases published

Packages

No packages published

Languages