Environments with multi-agent interactions often result a rich set of modalities of behavior between agents due to the inherent suboptimality of decision making processes when agents settle for satisfactory decisions. However, existing algorithms for solving these dynamic games are strictly unimodal and fail to capture the intricate multimodal behaviors of the agents. In this paper, we propose MMELQGames (Multimodal Maximum-Entropy Linear Quadratic Games), a novel constrained multimodal maximum entropy formulation of the Differential Dynamic Programming algorithm for solving generalized Nash equilibria. By formulating the problem as a certain dynamic game with incomplete and asymmetric information where agents are uncertain about the cost and dynamics of the game itself, the proposed method is able to reason about multiple local generalized Nash equilibria, enforce constraints with the Augmented Lagrangian framework and also perform Bayesian inference on the latent mode from past observations. We assess the efficacy of the proposed algorithm on two illustrative examples: multi-agent collision avoidance and autonomous racing. In particular, we show that only MMELQGames is able to effectively block a rear vehicle when given a speed disadvantage and the rear vehicle can overtake from multiple positions.
Entropy Regularization in Mean-Field Games of Optimal Stopping
University of Rome Tor Vergata(罗马托尔维加塔大学);ENSae-CREST, Institut Polytechnique de Paris(巴黎理工学院ENSae-CREST);Center for Mathematical Economics, Bielefeld University(比勒费尔德大学数学经济中心);Stanford University(斯坦福大学)
Entropy Regularization for Mean Field Games with Learning
University of California, Berkeley(加州大学伯克利分校);Amazon Research(亚马逊研究院);University of Southern California(南加州大学);University of Oxford(牛津大学);The University of Texas at Austin(德克萨斯大学奥斯汀分校);Oxford-Man Institute, University of Oxford(牛津大学牛津曼研究所)
An entropy minimization approach to second-order variational mean-field games
INRIA-Paris, MOKAPLAN(法国国家信息与自动化研究所巴黎分部,MOKAPLAN项目组);CEREMADE, UMR CNRS 7534, Université Paris IX Dauphine(巴黎第九大学,CNRS 7534联合研究实验室(CEREMADE));Indam, Unità SNS, Pisa, Italy(意大利比萨,意大利国家高等研究院数学与应用研究所(SNS));CNRS(法国国家科学研究中心)
Equilibrium for Time-inconsistent Mean Field Games: A Systematic Analysis by Entropy Regularization
University of Michigan(密歇根大学);Zhongtai Securities Institute for Financial Studies, Shandong University(山东大学中泰证券金融研究院);The Hong Kong Polytechnic University(香港理工大学);Tsinghua University(清华大学)