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.”
Original language | English |
---|---|
Title of host publication | Proceedings Robotics: Science and System XVIII |
Editors | Kris Hauser, Dylan Shell, Shoudong Huang |
Publisher | Robotics Science and Systems (RSS) |
Number of pages | 12 |
ISBN (Electronic) | 978-0-9923747-8-5 |
Publication status | Published - 2022 |
Event | Robotics: Science and Systems 2022 - New York, United States Duration: 27 Jun 2022 → 1 Jul 2022 |
Conference
Conference | Robotics: Science and Systems 2022 |
---|---|
Country/Territory | United States |
City | New York |
Period | 27/06/22 → 1/07/22 |