バリア証明書の学習による訓練時違反ゼロの安全強化学習
Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations
安全だが報酬の乏しい初期方策のみから、バリア証明書・ダイナミクスモデル・方策を交互に学習し、訓練中の安全違反をゼロに保つ安全RL手法CRABSを提案した論文。
著者: Yuping Luo, Tengyu Ma
分類: cs.LG, cs.AI, cs.RO, cs.SY, eess.SY
原文アブストラクト
Training-time safety violations have been a major concern when we deploy reinforcement learning algorithms in the real world. This paper explores the possibility of safe RL algorithms with zero training-time safety violations in the challenging setting where we are only given a safe but trivial-reward initial policy without any prior knowledge of the dynamics model and additional offline data. We propose an algorithm, Co-trained Barrier Certificate for Safe RL (CRABS), which iteratively learns barrier certificates, dynamics models, and policies. The barrier certificates, learned via adversarial training, ensure the policy's safety assuming calibrated learned dynamics model. We also add a regularization term to encourage larger certified regions to enable better exploration. Empirical simulations show that zero safety violations are already challenging for a suite of simple environments with only 2-4 dimensional state space, especially if high-reward policies have to visit regions near the safety boundary. Prior methods require hundreds of violations to achieve decent rewards on these tasks, whereas our proposed algorithms incur zero violations.
