This work Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning appeared at the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024)
This codebase is based on PyMARL and contains the implementation of the GACG algorithm.
Tasks can be found in src/envs.
To run experiments on SMAC benchmark:
python src/main.py --config=gacg --env-config=sc2 with env_args.map_name='10m_vs_11m' The requirements.txt file can be used to install the necessary packages into a virtual environment.
- QMIX: QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
- DCG: Deep Coordination Graphs
- DICG: Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
- CASEC: Context-Aware Sparse Deep Coordination Graphs
- VAST: VAST: Value Function Factorization with Variable Agent Sub-Teams
If you use GACG in your research, please cite the GACG.
Wei Duan, Jie Lu, Junyu Xuan. Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning. CoRR abs/2404.10976 (2024)
In BibTeX format:
@inproceedings{ijcai2024p434,
title = {Group-Aware Coordination Graph for Multi-Agent Reinforcement Learning},
author = {Duan, Wei and Lu, Jie and Xuan, Junyu},
booktitle = {Proceedings of the Thirty-Third International Joint Conference on
Artificial Intelligence, {IJCAI-24}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Kate Larson},
pages = {3926--3934},
year = {2024},
month = {8},
note = {Main Track},
doi = {10.24963/ijcai.2024/434},
url = {https://doi.org/10.24963/ijcai.2024/434},
}