paper-with-me

Papers

Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning

2024-12-25 · Yassine Chemingui, Aryan Deshwal, Honghao Wei, Alan Fern, Janardhan Rao Doppa

Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during deployment without retraining remains an under-explored challenge. To address this challenge, we introduce constraint-adaptive policy switching (CAPS), a wrapper framework around existing offline RL algorithms. During training, CAPS uses offline data to learn multiple policies with a shared representation that optimize different reward and cost trade-offs. During testing, CAPS switches between those policies by selecting at each state the policy that maximizes future rewards among those that satisfy the current cost constraint. Our experiments on 38 tasks from the DSRL benchmark demonstrate that CAPS consistently outperforms existing methods, establishing a strong wrapper-based baseline for OSRL. The code is publicly available at https://github.com/yassineCh/CAPS.

📄 PDF Abstract BibTeX arXiv:2412.18946

Code (1)

yassinech/caps 공식 구현 pytorch

Tasks

Decision MakingOffline RLreinforcement-learningReinforcement LearningSafe Reinforcement Learning

Similar Papers 제목 키워드 기반

Constrained Decision Transformer for Offline Safe Reinforcement Learning

2023-02-14 · Zuxin Liu, Zijian Guo, Yihang Yao, Zhepeng Cen 외

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the environment. We aim to tackle a more challenging problem: learning a safe policy from an offline dataset. We study the offl…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

Evaluation-Time Policy Switching for Offline Reinforcement Learning

2025-03-15 · Natinael Solomon Neggatu, Jeremie Houssineau, Giovanni Montana

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offl…

Behavioural cloningOffline RLreinforcement-learningReinforcement Learning+1

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model

2024-01-19 · Yinan Zheng, Jianxiong Li, Dongjie Yu, Yujie Yang 외

Safe offline RL is a promising way to bypass risky online interactions towards safe policy learning. Most existing methods only enforce soft constraints, i.e., constraining safety violations in expectation below threshol…

Offline RLreinforcement-learningReinforcement Learning

Marvel: Accelerating Safe Online Reinforcement Learning with Finetuned Offline Policy

2024-12-05 · Keru Chen, Honghao Wei, Zhigang Deng, Sen Lin

The high costs and risks involved in extensive environment interactions hinder the practical application of current online safe reinforcement learning (RL) methods. While offline safe RL addresses this by learning polici…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning

SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations

2023-09-21 · NeurIPS 2023 11

We consider offline safe imitation learning (IL), where the agent aims to learn the safe policy that mimics preferred behavior while avoiding non-preferred behavior from non-preferred demonstrations and unlabeled demonst…