Learning Mixed Strategies in Trajectory Games
L. Peters (TU Delft - Learning & Autonomous Control)
David Fridovich-Keil (The University of Texas at Austin)
L. Ferranti (TU Delft - Learning & Autonomous Control)
Cyrill Stachniss (Universität Bonn)
J. Alonso-Mora (TU Delft - Learning & Autonomous Control)
Forrest Laine (Vanderbilt University)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
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.”