Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning

arXiv:2311.00865v2 Announce Type: replace
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 …

agent arxiv cs.ai cs.lg cs.ma cs.ro multi-agent reinforcement reinforcement learning type