arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11895cs.AIcs.RO
收藏

基于迭代推理的强化学习在密集业务合并中的应用

Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic

Stanford University(斯坦福大学);Toyota Research Institute(丰田研究所);Honda Research Institute(本田研究所)

Maxime Bouton, Alireza Nakhaei, David Isele, Kikuo Fujimura, Mykel J. Kochenderfer

摘要:

对于自动驾驶汽车来说,在密集的交通中进行机动是一项具有挑战性的任务,因为它需要对许多其他参与者的随机行为进行推理。此外,智能体必须在有限的时间和距离内完成机动。在这项工作中,我们提出了一个结合强化学习和博弈论来学习合并行为。我们设计了一个训练课程的强化学习代理使用水平的概念,$k$行为。这种方法在训练期间将代理暴露于各种各样的行为,这促进了对模型差异鲁棒的学习策略。我们表明,我们的方法比传统的训练方法学习更有效的政策。

英文摘要:

Maneuvering in dense traffic is a challenging task for autonomous vehicles because it requires reasoning about the stochastic behaviors of many other participants. In addition, the agent must achieve the maneuver within a limited time and distance. In this work, we propose a combination of reinforcement learning and game theory to learn merging behaviors. We design a training curriculum for a reinforcement learning agent using the concept of level-$k$ behavior. This approach exposes the agent to a broad variety of behaviors during training, which promotes learning policies that are robust to model discrepancies. We show that our approach learns more efficient policies than traditional training methods.

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。

↑