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 2004.12678cs.LGstat.ML
收藏

多样性在行动:一般和多智能体连续逆最优控制

Diversity in Action: General-Sum Multi-Agent Continuous Inverse Optimal Control

Mercedes-Benz AG(梅赛德斯-奔驰股份公司);TU Delft(代尔夫特理工大学)

Christian Muench, Frans A. Oliehoek, Dariu M. Gavrila

摘要:

交通场景具有内在的交互性。多个决策者预测其他人的行动,并选择最大化其回报的策略。我们从博弈论的角度来看待这些互动,这引入了各种挑战。人类并不是完全理性的,他们的奖励需要从真实世界的数据中推断出来,任何预测算法都需要具有实时能力,以便我们可以在自动驾驶汽车(AV)中使用它。在这项工作中,我们提出了一个博弈论的方法,解决了上述所有问题。与许多现有的用于AV的方法相比,我们的方法1)不需要完美的通信,2)允许每个代理单独奖励。我们的实验表明,这些更现实的假设导致定性和定量不同的奖励推理和预测未来的行动,更好地匹配预期的现实世界的行为。

英文摘要:

Traffic scenarios are inherently interactive. Multiple decision-makers predict the actions of others and choose strategies that maximize their rewards. We view these interactions from the perspective of game theory which introduces various challenges. Humans are not entirely rational, their rewards need to be inferred from real-world data, and any prediction algorithm needs to be real-time capable so that we can use it in an autonomous vehicle (AV). In this work, we present a game-theoretic method that addresses all of the points above. Compared to many existing methods used for AVs, our approach does 1) not require perfect communication, and 2) allows for individual rewards per agent. Our experiments demonstrate that these more realistic assumptions lead to qualitatively and quantitatively different reward inference and prediction of future actions that match better with expected real-world behaviour.

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。

↑