Multi-agent teaming achieves better performance when there is communication among participating agents allowing them to coordinate their actions for maximizing shared utility. However, when collaborating a team of agents with different action and observation spaces, information sharing is not straightforward and requires customized communication protocols, depending on sender and receiver types. Without properly modeling such heterogeneity in agents, communication becomes less helpful and could even deteriorate the multi-agent cooperation performance. We propose heterogeneous graph attention networks, called HetNet, to learn efficient and diverse communication models for coordinating heterogeneous agents towards accomplishing tasks that are of collaborative nature. We propose a Multi-Agent Heterogeneous Actor-Critic (MAHAC) learning paradigm to obtain collaborative per-class policies and effective communication protocols for composite robot teams. Our proposed framework is evaluated against multiple baselines in a complex environment in which agents of different types must communicate and cooperate to satisfy the objectives. Experimental results show that HetNet outperforms the baselines in learning sophisticated multi-agent communication protocols by achieving $\sim$10\% improvements in performance metrics.
翻译:多试剂团队在参与机构之间进行沟通,使其能够协调行动,最大限度地发挥共同效用时取得更好的业绩。然而,如果一个具有不同行动和观测空间的代理团队合作,信息共享并非直截了当,需要根据发送者和接收者类型制定定制的通信协议。如果代理机构不适当地建模,通信将变得不那么有用,甚至可能恶化多试剂合作绩效。我们提议了名为HetNet的混合图形关注网络,以学习高效和多样的通信模式,协调不同代理机构,从而完成具有协作性质的任务。我们提议了一个多源多源多源多源的Actor-Crict(MAHAC)学习模式,以便为复合机器人团队获得每类协作政策和有效通信协议。我们提议的框架是在复杂的环境中根据多个基线进行评估的,在这个环境中,不同类型的代理机构必须进行沟通与合作,以实现各项目标。实验结果显示,HetNet在学习复杂的多试剂通信协议方面超越了基线,在绩效指标上实现了$sim10 ⁇ 的改进。