多智能体路径搜索中的学习选择通信
Learning Selective Communication for Multi-Agent Path Finding
摘要：
通过深度强化学习（RL）或模仿学习（IL）进行学习通信最近已被证明是解决多智能体路径查找（MAPF）的有效方法。然而，现有的基于通信的MAPF求解器专注于广播通信，其中代理将其消息广播到所有其他或预定义的代理。它不仅不切实际，而且会导致冗余信息，甚至可能损害多智能体合作。一个简洁的通信方案应该了解哪些信息是相关的，并影响每个代理的决策过程。为了解决这个问题，我们考虑了一个请求-答复的情况下，并提出了决策因果通信（DCC），一个简单而有效的模型，使代理选择邻居进行通信在训练和执行。具体地说，只有当一个邻居的存在导致中央代理的决策调整时，这个邻居才被确定为相关的和有影响力的。这种判断仅基于Agent的局部观察来学习，因此适合于分散执行来处理大规模问题。在障碍物丰富的环境中的实证评估表明，我们的方法具有低通信开销的高成功率。
英文摘要：
Learning communication via deep reinforcement learning (RL) or imitation learning (IL) has recently been shown to be an effective way to solve Multi-Agent Path Finding (MAPF). However, existing communication based MAPF solvers focus on broadcast communication, where an agent broadcasts its message to all other or predefined agents. It is not only impractical but also leads to redundant information that could even impair the multi-agent cooperation. A succinct communication scheme should learn which information is relevant and influential to each agent's decision making process. To address this problem, we consider a request-reply scenario and propose Decision Causal Communication (DCC), a simple yet efficient model to enable agents to select neighbors to conduct communication during both training and execution. Specifically, a neighbor is determined as relevant and influential only when the presence of this neighbor causes the decision adjustment on the central agent. This judgment is learned only based on agent's local observation and thus suitable for decentralized execution to handle large scale problems. Empirical evaluation in obstacle-rich environment indicates the high success rate with low communication overhead of our method.
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。
