FOSP: ワールドモデルによるオフライン安全方策のファインチューニング
FOSP: Fine-tuning Offline Safe Policy through World Models
オフラインで学習した安全方策を、到達可能性ガイダンス付きのモデルベースRLでオンライン微調整し、未知の安全制約シナリオへの汎化を改善する手法を提案。
著者: Chenyang Cao, Yucheng Xin, Silang Wu, Longxiang He, Zichen Yan, Junbo Tan, Xueqian Wang
分類: cs.RO, cs.LG
原文アブストラクト
Offline Safe Reinforcement Learning (RL) seeks to address safety constraints by learning from static datasets and restricting exploration. However, these approaches heavily rely on the dataset and struggle to generalize to unseen scenarios safely. In this paper, we aim to improve safety during the deployment of vision-based robotic tasks through online fine-tuning an offline pretrained policy. To facilitate effective fine-tuning, we introduce model-based RL, which is known for its data efficiency. Specifically, our method employs in-sample optimization to improve offline training efficiency while incorporating reachability guidance to ensure safety. After obtaining an offline safe policy, a safe policy expansion approach is leveraged for online fine-tuning. The performance of our method is validated on simulation benchmarks with five vision-only tasks and through real-world robot deployment using limited data. It demonstrates that our approach significantly improves the generalization of offline policies to unseen safety-constrained scenarios. To the best of our knowledge, this is the first work to explore offline-to-online RL for safe generalization tasks.
