Learning Mixed Strategies in Trajectory Games


Lasse Peters (Delft University of Technology),
David Fridovich-Keil (Stanford University),
Laura Ferranti (Delft University of Technology),
Cyrill Stachniss (University of Bonn),
Javier Alonso-Mora (Delft University of Technology),
Forrest J Laine (UC Berkeley)
Paper Website
Paper #051
Session 11. Short talks


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.”

Previous Paper Paper Website Next Paper