arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.00558cs.MA
收藏

异步协作多智能体强化学习与有限通信

Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication

Massachusetts Institute of Technology(麻省理工学院)

Sydney Dolan, Siddharth Nayak, Jasmine Jerry Aloor, Hamsa Balakrishnan

AI总结:

本研究提出了一种异步多智能体强化学习框架AsynCoMARL,通过图Transformer学习动态图中的通信协议,在通信受限环境下实现高效协作,相比传统同步方法,减少26%的通信量同时保持相近的成功率和碰撞率。

摘要:

我们考虑了多个自主智能体必须在未知且通信受限的环境中协作导航和执行任务的问题设置。传统多智能体强化学习(MARL)方法假设同步通信,在此类环境中表现不佳。我们提出AsynCoMARL,一种异步MARL方法,利用图Transformer从动态图中学习通信协议。AsynCoMARL能够适应智能体之间不频繁且异步的通信,图中的边仅在智能体之间通信时形成。我们证明,尽管智能体之间传递的消息减少了26%,AsynCoMARL在成功率和碰撞率方面仍与领先基线相当。

英文摘要:

We consider the problem setting in which multiple autonomous agents must cooperatively navigate and perform tasks in an unknown, communication-constrained environment. Traditional multi-agent reinforcement learning (MARL) approaches assume synchronous communications and perform poorly in such environments. We propose AsynCoMARL, an asynchronous MARL approach that uses graph transformers to learn communication protocols from dynamic graphs. AsynCoMARL can accommodate infrequent and asynchronous communications between agents, with edges of the graph only forming when agents communicate with each other. We show that AsynCoMARL achieves similar success and collision rates as leading baselines, despite 26\% fewer messages being passed between agents.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑