arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.01202cs.LGcs.MAstat.ML
收藏

多Agent团队中可迁移合作行为的学习

Learning Transferable Cooperative Behavior in Multi-Agent Teams

Carnegie Mellon University(卡内基梅隆大学)

Akshat Agarwal, Sumit Kumar, Katia Sycara

摘要:

虽然多智能体交互可以自然地建模为图,但环境传统上被认为是黑盒。我们建议创建一个共享的代理实体图,其中代理和环境实体形成顶点,顶点之间存在边,可以相互通信。智能体通过沿着图的边交换消息来学习合作。我们提出的多智能体强化学习框架对系统中存在的代理或实体的数量以及排列不变性是不变的,这两者对于任何多智能体系统表示都是理想的属性。我们提出了国家的最先进的结果覆盖,形成和线控制任务的多智能体团队在一个完全分散的框架,并进一步表明,学习的政策迅速转移到不同的团队规模的情况下,随着强大的zero-shot泛化性能。这是朝着开发多智能体团队迈出的重要一步,这些团队可以在现实世界中实际部署,而无需假设完全的先验知识或无限距离的即时通信。

英文摘要:

While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. We propose to create a shared agent-entity graph, where agents and environmental entities form vertices, and edges exist between the vertices which can communicate with each other. Agents learn to cooperate by exchanging messages along the edges of this graph. Our proposed multi-agent reinforcement learning framework is invariant to the number of agents or entities present in the system as well as permutation invariance, both of which are desirable properties for any multi-agent system representation. We present state-of-the-art results on coverage, formation and line control tasks for multi-agent teams in a fully decentralized framework and further show that the learned policies quickly transfer to scenarios with different team sizes along with strong zero-shot generalization performance. This is an important step towards developing multi-agent teams which can be realistically deployed in the real world without assuming complete prior knowledge or instantaneous communication at unbounded distances.

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。

↑