Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning
Matthias Gerstgrasser, Tom Danino, Sarah Keren
Abstract
We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized Experience Relay, in which agents share with other agents a limited number of transitions they observe during training. The intuition behind this is that even a small number of relevant experiences from other agents could help each agent learn. Unlike many other multi-agent RL algorithms, this approach allows for largely decentralized training, requiring only a limited communication channel between agents. We show that our approach outperforms baseline no-sharing decentralized training and state-of-the art multi-agent RL algorithms. Further, sharing only a small number of highly relevant experiences outperforms sharing all experiences between agents, and the performance uplift from selective experience sharing is robust across a range of hyperparameters and DQN variants.
BibTeX
@inproceedings{
gerstgrasser2023selectively,
title={Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning},
author={Matthias Gerstgrasser and Tom Danino and Sarah Keren},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=DpuphOgJqh}
}