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 1703.03121cs.LG
收藏

多Agent协作模仿学习

Coordinated Multi-Agent Imitation Learning

California Institute of Technology(加州理工学院);Disney Research(迪士尼研究院);STATS LLC(STATS有限责任公司)

Hoang M. Le, Yisong Yue, Peter Carr, Patrick Lucey

摘要:

我们从多个协调代理的演示中研究了模仿学习问题。在这种情况下,一个关键的挑战是,学习一个良好的协调模式可能是困难的,因为协调往往是隐含在示范,必须推断为一个潜在的变量。我们提出了一种联合的方法,同时学习一个潜在的协调模型以及个人的政策。特别是,我们的方法集成了无监督结构学习与传统的模仿学习。我们说明了我们的方法的力量学习多个政策的细粒度的行为建模在团队运动中,不同的球员在协调的团队策略中扮演不同的角色的一个困难的问题。我们发现,有一个协调模型来推断玩家的角色产生了显着改善模仿损失相比,传统的基线。

英文摘要:

We study the problem of imitation learning from demonstrations of multiple coordinating agents. One key challenge in this setting is that learning a good model of coordination can be difficult, since coordination is often implicit in the demonstrations and must be inferred as a latent variable. We propose a joint approach that simultaneously learns a latent coordination model along with the individual policies. In particular, our method integrates unsupervised structure learning with conventional imitation learning. We illustrate the power of our approach on a difficult problem of learning multiple policies for fine-grained behavior modeling in team sports, where different players occupy different roles in the coordinated team strategy. We show that having a coordination model to infer the roles of players yields substantially improved imitation loss compared to conventional baselines.

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。

↑