Abstract:
Following the success of the first two editions at IROS'23 and ICRA'24, the 3rd MAD-Games workshop at ACC 2026 aims to explore the latest advances in using game-theoretic and multi-agent control and learning approaches to help autonomous agents achieve safe interactions in highly dynamic environments. One of the key challenges in designing effective multi-agent decision-making algorithms is handling the complex and highly interactive behaviors among agents. Existing game-theoretic methods often rely on an oversimplified discretization of agent action spaces and strong assumptions such as perfect information and rational decision-making, which can lead to inaccurate descriptions of the dynamics of real-world interactions. Additionally, real-world autonomous systems' highly dynamic and unpredictable nature can make it difficult to predict the system's behavior, leading to safety risks. These dynamic games are inherently challenging as (a) crashing is dangerous and expensive, (b) current sensors alone cannot reliably infer the intention or strategy of the opponents, and (c) we are in a small-data regime, as we cannot directly use past games to learn from, as agent strategies and environments may change over time. The MAD-Games workshop focuses on addressing these challenges by bringing together researchers and practitioners to (1) explore the latest developments in interactive autonomy, e.g., game theory, distributed control, and multi-agent learning, and (2) investigate how game-theoretic models can be adapted to handle the complexities of real-world systems.
Organizers:
Professor
Department of Electrical and Systems Engineering
University of Pennsylvania
Assistant Professor
Department of Mechanical Engineering and Mechanics
Lehigh University
David & Andrew Lewis Chair, Professor
Daniel Guggenheim School of Aerospace Engineering
Georgia Tech
