多項式ゾノトープと到達可能性解析を用いた行動投影による証明可能な安全強化学習
Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
強化学習エージェントの行動を安全な行動に投影する安全シールドを提案し、多項式ゾノトープによる到達可能性解析で非線形連続システムの安全性を保証する。
著者: Niklas Kochdumper, Hanna Krasowski, Xiao Wang, Stanley Bak, Matthias Althoff
分類: cs.RO, cs.LG, cs.SY, eess.SY
原文アブストラクト
While reinforcement learning produces very promising results for many applications, its main disadvantage is the lack of safety guarantees, which prevents its use in safety-critical systems. In this work, we address this issue by a safety shield for nonlinear continuous systems that solve reach-avoid tasks. Our safety shield prevents applying potentially unsafe actions from a reinforcement learning agent by projecting the proposed action to the closest safe action. This approach is called action projection and is implemented via mixed-integer optimization. The safety constraints for action projection are obtained by applying parameterized reachability analysis using polynomial zonotopes, which enables to accurately capture the nonlinear effects of the actions on the system. In contrast to other state-of-the-art approaches for action projection, our safety shield can efficiently handle input constraints and dynamic obstacles, eases incorporation of the spatial robot dimensions into the safety constraints, guarantees robust safety despite process noise and measurement errors, and is well suited for high-dimensional systems, as we demonstrate on several challenging benchmark systems.
