Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
Abstract
Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three different classes of MARL algorithms (independent learning, centralised multi-agent policy gradient, value decomposition) in a diverse range of cooperative multi-agent learning tasks. Our experiments serve as a reference for the expected performance of algorithms across different learning tasks, and we provide insights regarding the effectiveness of different learning approaches. We open-source EPyMARL, which extends the PyMARL codebase to include additional algorithms and allow for flexible configuration of algorithm implementation details such as parameter sharing. Finally, we open-source two environments for multi-agent research which focus on coordination under sparse rewards.
Cite
@article{arxiv.2006.07869,
title = {Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks},
author = {Georgios Papoudakis and Filippos Christianos and Lukas Schäfer and Stefano V. Albrecht},
journal= {arXiv preprint arXiv:2006.07869},
year = {2021}
}
Comments
Published in 35th Conference on Neural Information Processing Systems (NeurIPS 2021) Track on Datasets and Benchmarks