ICML 2021oral137 citations

Cooperative Exploration for Multi-Agent Deep Reinforcement Learning

Iou-Jen Liu, Unnat Jain, Raymond A Yeh, Alexander Schwing

Abstract

Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE): agents share a common goal while exploring. The goal is selected from multiple projected state spaces by a normalized entropy-based technique. Then, agents are trained to reach the goal in a coordinated manner. We demonstrate that CMAE consistently outperforms baselines on various tasks, including a sparse-reward version of multiple-particle environment (MPE) and the Starcraft multi-agent challenge (SMAC).

BibTeX
@InProceedings{pmlr-v139-liu21j,
  title = 	 {Cooperative Exploration for Multi-Agent Deep Reinforcement Learning},
  author =       {Liu, Iou-Jen and Jain, Unnat and Yeh, Raymond A and Schwing, Alexander},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {6826--6836},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/liu21j/liu21j.pdf},
  url = 	 {https://proceedings.mlr.press/v139/liu21j.html},
  abstract = 	 {Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE): agents share a common goal while exploring. The goal is selected from multiple projected state spaces by a normalized entropy-based technique. Then, agents are trained to reach the goal in a coordinated manner. We demonstrate that CMAE consistently outperforms baselines on various tasks, including a sparse-reward version of multiple-particle environment (MPE) and the Starcraft multi-agent challenge (SMAC).}
}
Cooperative Exploration for Multi-Agent Deep Reinforcement Learning · ICML 2021