The paper introduces Q-learning Penalized Transformer (QPT), a training–inference consistent framework for safe offline reinforcement learning. QPT trains a Transformer policy that generates actions conditioned on trajectory context and target return/cost while incorporating a Q-shaped penalty to balance safety, reward maximization, and behavior regularization. The method consistently outperforms strong baselines on 38 DSRL benchmark tasks and adapts robustly to varying constraint thresholds.
arXiv:2610.34208v1 Announce Type: cross
Abstract: Offline safe reinforcement learning (RL) learns safety-aware policies from static datasets while satisfying safety constraints during deployment. Mot...
By Changxu Ni, Feiran You, Yongan Guo, Hongyang Du, Kang Wei, Le Liang, Yiyang Ni, Jun Li
arXiv:2607. 03903v1 Announce Type: new Abstract: Multi-task offline safe reinforcement learning (RL) promises to learn a shared optimal safe policy from offline data across multiple tasks.
By Jiayi Guan, Tianle Zhang, Li Shen, Ruiqi Zhang, Ao Zhou, Lusong Li, Guai Chen, Mengjie Li, Alois Knoll, Xiaodong He, Changjun Jiang
The paper introduces Q-Target Pretrained Transformers (QTPT), a method that replaces supervised behavior cloning with a Bellman-style Q‑target objective for in‑context reinforcement learning. QTPT retains the context‑conditioned Transformer architecture but learns to estimate action values using rewards and transitions from the context, rather than merely imitating offline actions. The authors provide theoretical analysis in stochastic linear bandits and finite‑horizon MDPs, demonstrating improved robustness to weak or suboptimal data, and empirically show gains over supervised pretraining on controlled RL benchmarks and extensions to D4RL Kitchen and AntMaze.
By Yichen Lin, Xuyuan Xiong, Xue Wang, Xiangfu Meng, Mike Mingcheng Wei, Tao Yao
arXiv:2608. 19684v1 Announce Type: new Abstract: Recent studies investigate how to leverage pre-collected datasets to improve the policy performance and sample efficiency of RL.
By Tanachai Anakewat, Takayuki Osa, Tatsuya Harada
arXiv:2608.20909v1 Announce Type: new
Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
By Xuyao Lin, Yixiang Shan, Jinru Duan, Tao Yang, Xinyu Zhao, Runyu Lei, Yiming Zhao, Jiaxin Fan, Zongbao Feng, Peng Jia
arXiv:2603. 15136v2 Announce Type: replace-cross Abstract: Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints.
By Mumuksh Tayal, Manan Tayal, Ravi Prakash
The paper presents a unified framework for regularization-based robust reinforcement learning by deriving upper bounds on the performance gap between nominal and worst-case policies. These bounds are expressed as a regularization objective plus a KL-divergence penalty, explaining why KL penalties enhance robustness. The authors reformulate robust training as a constrained optimization problem, updating the Lagrange multiplier jointly with the policy to automatically tune regularization, and validate the approach with extensive adversarial evaluations on continuous control tasks.
By Amine Andam, Jamal Bentahar, Mustapha Hedabou
arXiv:2504. 12557v3 Announce Type: replace-cross Abstract: Ensuring safe behavior in reinforcement learning (RL) is challenging when safety constraints are implicit and cannot be densely measured.
By Siow Meng Low, Ze Gong, Akshat Kumar
arXiv:2608. 10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient exposure to safety-critical driving scenes.
By Xincong Hu (Nanjing University), Lei Ou (Nanjing University), Maosen Li (Yinwang Intelligent Technology Co., Ltd), Jingtao Zhang (Yinwang Intelligent Technology Co., Ltd), Liguo Hou (Yinwang Intelligent Technology Co., Ltd), Zongzhang Zhang (Nanjing University)
arXiv:2610.19783v1 Announce Type: new
Abstract: Reinforcement learning (RL) holds the promise of learning a policy that can outperform what is shown in the data. However, in practice, such systems su...
By Zhiyuan Zhou, Sergey Levine
The paper introduces Zeroth-Order Log-Barrier Policy Gradient (ZO‑LBPG), a reward‑model‑free method for safe reinforcement learning from human feedback (Safe‑RLHF). ZO‑LBPG optimizes a log‑barrier objective using zeroth‑order estimates derived directly from human preferences, and incorporates conservative constraint margins, coupled rollouts, and an adaptive step size to keep every policy executed during training strictly feasible. The authors prove high‑probability feasibility of all iterates and exploration policies, establish global convergence to an approximately optimal constrained policy, and provide sample complexity bounds for trajectories and human queries, with experimental validation on a synthetic CMDP and a language‑model alignment task.