FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis
This work addresses the challenge of robust and adaptive autonomous vehicle deployment in multi-agent environments, with incremental improvements in opponent modeling and risk management.
The paper tackled the problem of balancing performance and safety in autonomous racing by developing a method for generating diverse opponents and a robust online adaptation strategy, resulting in autonomous vehicles achieving scaled speeds comparable to Formula One racecars.
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.