Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

arXiv:2307.12062v2 Announce Type: replace
Abstract: Deploying reinforcement learning (RL) systems requires robustness to uncertainty and model misspecification, yet prior robust RL methods typically only study noise introduced independently across time. However, practical sources of uncertainty are usually coupled across time. We formally introduce temporally-coupled perturbations, presenting a novel challenge for existing robust RL methods. To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game. By …

abstract arxiv challenge cs.ai cs.lg game however noise novel practical presenting prior reinforcement reinforcement learning robust robustness study systems type uncertainty