paper-with-me

Papers

Feasibility-Aware Pessimistic Estimation: Toward Long-Horizon Safety in Offline RL

2025-05-13 · Zhikun Tao, Gang Xiong, He Fang, Zhen Shen, Yunjun Han, Qing-Shan Jia

Offline safe reinforcement learning(OSRL) derives constraint-satisfying policies from pre-collected datasets, offers a promising avenue for deploying RL in safety-critical real-world domains such as robotics. However, the majority of existing approaches emphasize only short-term safety, neglecting long-horizon considerations. Consequently, they may violate safety constraints and fail to ensure sustained protection during online deployment. Moreover, the learned policies often struggle to handle states and actions that are not present or out-of-distribution(OOD) from the offline dataset, and exhibit limited sample efficiency. To address these challenges, we propose a novel framework Feasibility-Aware offline Safe Reinforcement Learning with CVAE-based Pessimism (FASP). First, we employ Hamilton-Jacobi (H-J) reachability analysis to generate reliable safety labels, which serve as supervisory signals for training both a conditional variational autoencoder (CVAE) and a safety classifier. This approach not only ensures high sampling efficiency but also provides rigorous long-horizon safety guarantees. Furthermore, we utilize pessimistic estimation methods to estimate the Q-value of reward and cost, which mitigates the extrapolation errors induces by OOD actions, and penalize unsafe actions to enabled the agent to proactively avoid high-risk behaviors. Moreover, we theoretically prove the validity of this pessimistic estimation. Extensive experiments on DSRL benchmarks demonstrate that FASP algorithm achieves competitive performance across multiple experimental tasks, particularly outperforming state-of-the-art algorithms in terms of safety.

📄 PDF Abstract BibTeX arXiv:2505.08179

Code (0)

등록된 구현이 없습니다.

Tasks

Offline RLSafe Reinforcement Learning

Similar Papers 제목 키워드 기반

Feasibility-Guided Safety-Aware Model Predictive Control for Jump Markov Linear Systems

2023-10-21 · Zakariya Laouar, Qi Heng Ho, Rayan Mazouz, Tyler Becker 외

In this paper, we present a controller framework that synthesizes control policies for Jump Markov Linear Systems subject to stochastic mode switches and imperfect mode estimation. Our approach builds on safe and robust …

Model Predictive ControlState Estimation

Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity

2022-02-28 · Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen 외

Offline or batch reinforcement learning seeks to learn a near-optimal policy using history data without active exploration of the environment. To counter the insufficient coverage and sample scarcity of many offline data…

Offline RLQ-Learningreinforcement-learningReinforcement Learning (RL)

Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds

2024-08-16 · Zhiyong Wang, Dongruo Zhou, John C. S. Lui, Wen Sun

Learning a transition model via Maximum Likelihood Estimation (MLE) followed by planning inside the learned model is perhaps the most standard and simplest Model-based Reinforcement Learning (RL) framework. In this work,…

Model-based Reinforcement LearningOffline RLReinforcement Learning (RL)

Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation

2024-12-15 · Juntao Dai, Yaodong Yang, Qian Zheng, Gang Pan

A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantag…

reinforcement-learningReinforcement LearningSafe Reinforcement Learning

SAFE: Stable Alignment Finetuning with Entropy-Aware Predictive Control for Reinforcement Learning from Human Feedback (RLHF)

2026-02-04 · Dipan Maity arxiv

Proximal Policy Optimization (PPO) has been positioned by recent literature as the canonical method for the RL part of Reinforcement Learning from Human Feedback (RLHF). PPO performs well empirically but has a heuristic …

Reinforcement Learning