Learning Mixed Strategies in Trajectory Games

TL;DR

This paper introduces a novel approach for multi-agent trajectory games that reduces online computation and enables the optimization of mixed strategies through a lifted game formulation, validated on pursuit-evasion scenarios.

Contribution

It presents an offline training method to lessen online computation and a lifted game framework for simultaneous optimization of multiple trajectories, enhancing strategic competitiveness.

Findings

Reduced online computational complexity.

Effective mixed strategy construction in trajectory games.

Validated improvements in pursuit-evasion experiments.

Abstract

In multi-agent settings, game theory is a natural framework for describing the strategic interactions of agents whose objectives depend upon one another's behavior. Trajectory games capture these complex effects by design. In competitive settings, this makes them a more faithful interaction model than traditional "predict then plan" approaches. However, current game-theoretic planning methods have important limitations. In this work, we propose two main contributions. First, we introduce an offline training phase which reduces the online computational burden of solving trajectory games. Second, we formulate a lifted game which allows players to optimize multiple candidate trajectories in unison and thereby construct more competitive "mixed" strategies. We validate our approach on a number of experiments using the pursuit-evasion game "tag."