Guardado en:
Detalles Bibliográficos
Autores principales: Bai, Wensong, Zhang, Chao, Xu, Qihang, Chen, Chufan, Zhou, Chenhao, Qian, Hui
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.08584
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910016548634624
author Bai, Wensong
Zhang, Chao
Xu, Qihang
Chen, Chufan
Zhou, Chenhao
Qian, Hui
author_facet Bai, Wensong
Zhang, Chao
Xu, Qihang
Chen, Chufan
Zhou, Chenhao
Qian, Hui
contents Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, necessitating a single policy that can adapt zero-shot to different cost thresholds. However, most existing offline safe RL methods are trained under a pre-specified threshold, yielding policies with limited generalization and deployment flexibility across cost thresholds. Motivated by recent progress in conditional sequence modeling (CSM), which enables flexible goal-conditioned control by specifying target returns, we propose RCDT, a CSM-based method that supports zero-shot deployment across multiple cost thresholds within a single trained policy. RCDT is the first CSM-based offline safe RL algorithm that integrates a Lagrangian-style cost penalty with an auto-adaptive penalty coefficient. To avoid overly conservative behavior and achieve a more favorable return--cost trade-off, a reward--cost-aware trajectory reweighting mechanism and Q-value regularization are further incorporated. Extensive experiments on the DSRL benchmark demonstrate that RCDT consistently improves return--cost trade-offs over representative baselines, advancing the state-of-the-art in offline safe RL.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08584
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Conditional Sequence Modeling for Safe Reinforcement Learning
Bai, Wensong
Zhang, Chao
Xu, Qihang
Chen, Chufan
Zhou, Chenhao
Qian, Hui
Machine Learning
Offline safe reinforcement learning (RL) aims to learn policies from a fixed dataset while maximizing performance under cumulative cost constraints. In practice, deployment requirements often vary across scenarios, necessitating a single policy that can adapt zero-shot to different cost thresholds. However, most existing offline safe RL methods are trained under a pre-specified threshold, yielding policies with limited generalization and deployment flexibility across cost thresholds. Motivated by recent progress in conditional sequence modeling (CSM), which enables flexible goal-conditioned control by specifying target returns, we propose RCDT, a CSM-based method that supports zero-shot deployment across multiple cost thresholds within a single trained policy. RCDT is the first CSM-based offline safe RL algorithm that integrates a Lagrangian-style cost penalty with an auto-adaptive penalty coefficient. To avoid overly conservative behavior and achieve a more favorable return--cost trade-off, a reward--cost-aware trajectory reweighting mechanism and Q-value regularization are further incorporated. Extensive experiments on the DSRL benchmark demonstrate that RCDT consistently improves return--cost trade-offs over representative baselines, advancing the state-of-the-art in offline safe RL.
title Conditional Sequence Modeling for Safe Reinforcement Learning
topic Machine Learning
url https://arxiv.org/abs/2602.08584