Skip to yearly menu bar Skip to main content


FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis

Aman Sinha · Matthew O'Kelly · Hongrui Zheng · Rahul Mangharam · John Duchi · Russ Tedrake


Keywords: [ Planning and Control ] [ Robotics ] [ Reinforcement Learning ] [ Online Learning / Bandits ] [ Reinforcement Learning - General ]


Balancing performance and safety is crucial to deploying autonomous vehicles in multi-agent environments. In particular, autonomous racing is a domain that penalizes safe but conservative policies, highlighting the need for robust, adaptive strategies. Current approaches either make simplifying assumptions about other agents or lack robust mechanisms for online adaptation. This work makes algorithmic contributions to both challenges. First, to generate a realistic, diverse set of opponents, we develop a novel method for self-play based on replica-exchange Markov chain Monte Carlo. Second, we propose a distributionally robust bandit optimization procedure that adaptively adjusts risk aversion relative to uncertainty in beliefs about opponents’ behaviors. We rigorously quantify the tradeoffs in performance and robustness when approximating these computations in real-time motion-planning, and we demonstrate our methods experimentally on autonomous vehicles that achieve scaled speeds comparable to Formula One racecars.

Chat is not available.