Multimodal Maximum Entropy Dynamic Games
This work addresses the challenge of modeling intricate multimodal interactions in multi-agent environments, which is crucial for applications like autonomous driving and robotics, representing an incremental improvement over existing unimodal methods.
The paper tackled the problem of capturing multimodal behaviors in multi-agent dynamic games by proposing MMELQGames, a novel algorithm that reasons about multiple local generalized Nash equilibria and enforces constraints, demonstrating its efficacy in scenarios like multi-agent collision avoidance and autonomous racing where it effectively blocks a rear vehicle with a speed disadvantage.
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.