arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06619cs.ROcs.AIcs.LG
收藏

学习潜在表征影响多Agent交互

Learning Latent Representations to Influence Multi-Agent Interaction

Stanford University(斯坦福大学);Virginia Tech(弗吉尼亚理工学院暨州立大学)

Annie Xie, Dylan P. Losey, Ryan Tolsma, Chelsea Finn, Dorsa Sadigh

摘要:

与人类或机器人进行无障碍交互是很困难的,因为这些智能体是不稳定的。他们更新自己的政策,以回应自我代理人的行为,自我代理人必须预测这些变化,以适应。受人类的启发,我们认识到机器人不需要明确地对另一个代理将做出的每个低级动作进行建模;相反,我们可以通过高级表示来捕获其他代理的潜在策略。我们提出了一个强化学习为基础的框架,学习代理的政策,自我代理确定其行为和其他代理的未来战略之间的关系的潜在表示。然后,自我代理人利用这些潜在的动态来影响其他代理人,有目的地引导他们采取适合共同适应的政策。在几个模拟域和现实世界的空气曲棍球比赛,我们的方法优于替代品,并学会影响其他代理。

英文摘要:

Seamlessly interacting with humans or robots is hard because these agents are non-stationary. They update their policy in response to the ego agent's behavior, and the ego agent must anticipate these changes to co-adapt. Inspired by humans, we recognize that robots do not need to explicitly model every low-level action another agent will make; instead, we can capture the latent strategy of other agents through high-level representations. We propose a reinforcement learning-based framework for learning latent representations of an agent's policy, where the ego agent identifies the relationship between its behavior and the other agent's future strategy. The ego agent then leverages these latent dynamics to influence the other agent, purposely guiding them towards policies suitable for co-adaptation. Across several simulated domains and a real-world air hockey game, our approach outperforms the alternatives and learns to influence the other agent.

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。

↑