MPOGames: Efficient Multimodal Partially Observable Dynamic Games

MPOGames: Efficient Multimodal Partially Observable Dynamic Games
复制标题

MPOGames:高效多模态部分可观察动态博弈

DOI:
--
复制
发表时间:
2022
期刊:
IEEE International Conference on Robotics and Automation
影响因子:
--
通讯作者:
Evangelos A. Theodorou
Evangelos A. Theodorou
中科院分区:
--
文献类型:
--
作者:
Oswin So;P. Drews;Thomas Balch;Velin D. Dimitrov;G. Rosman;Evangelos A. Theodorou

文献摘要

参考文献

被引文献

相似文献

博弈论方法在涉及丰富的多智能体交互的情况下,已成为规划和预测的流行方法。然而,这些方法通常假设存在一个局部纳什均衡,因此无法处理不同主体意图的不确定性。当最大熵(MaxEnt)动态博弈试图解决这个问题时,实际的方法是使用线性二次逼近来解决MaxEnt纳什均衡,这种方法仅限于单峰响应,不适合具有多个局部纳什均衡的场景。通过将问题重新表述为POMDP,我们提出了MPOGames,一种有效解决MaxEnt动态博弈的方法,该方法捕获了局部纳什均衡之间的相互作用。我们通过一个两智能体合并的案例研究表明了不确定性感知博弈论方法的重要性。最后,我们在1/10比例的汽车平台上通过硬件实验证明了我们的方法的实时性。
Game theoretic methods have become popular for planning and prediction in situations involving rich multi-agent interactions. However, these methods often assume the existence of a single local Nash equilibria and are hence unable to handle uncertainty in the intentions of different agents. While maximum entropy (MaxEnt) dynamic games try to address this issue, practical approaches solve for MaxEnt Nash equilibria using linear-quadratic approximations which are restricted to unimodal responses and unsuitable for scenarios with multiple local Nash equilibria. By reformulating the problem as a POMDP, we propose MPOGames, a method for efficiently solving MaxEnt dynamic games that captures the interactions between local Nash equilibria. We show the importance of uncertainty-aware game theoretic methods via a two-agent merge case study. Finally, we prove the real-time capabilities of our approach with hardware experiments on a 1/10th scale car platform.
DOI: 10.15607/rss.2020.xvi.091
发表时间: 2019-10
期刊: ArXiv
影响因子: --
作者:
Simon Le Cleac'h;M. Schwager;Zachary Manchester
通讯作者: Simon Le Cleac'h;M. Schwager;Zachary Manchester
DOI: 10.1109/icra48891.2023.10160799
发表时间: 2023
期刊: IEEE
影响因子: --
作者:
Zhu, Edward L.;Borrelli, Francesco
通讯作者: Borrelli, Francesco
DOI: 10.1109/lra.2021.3074880
发表时间: 2020-11
影响因子: 5.2
作者:
Simon Le Cleac’h;M. Schwager;Zachary Manchester
通讯作者: Simon Le Cleac’h;M. Schwager;Zachary Manchester
DOI: --
发表时间: 2019
期刊: --
影响因子: --
作者:
Matthew O'Kelly;Hongrui Zheng;D. Karthik;Rahul Mangharam
通讯作者: Matthew O'Kelly;Hongrui Zheng;D. Karthik;Rahul Mangharam
置信空间中的随机动态博弈
DOI: 10.1109/tro.2021.3075376
发表时间: 2021
影响因子: 7.8
作者:
Schwarting, Wilko;Pierson, Alyssa;Karaman, Sertac;Rus, Daniela
通讯作者: Rus, Daniela