arXiv:2603. 15136v2 Announce Type: replace-cross Abstract: Offline safe reinforcement learning (RL) seeks reward-maximizing policies from static datasets under strict safety constraints.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
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:2609.34426v2 Announce Type: replace Abstract: This paper addresses the problem of safe offline reinforcement learning, which involves training a policy to satisfy safety constraints using an of...
arXiv:2609.13231v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existing fine-tuning methods provid...
The paper introduces new evaluation metrics for safe reinforcement learning that go beyond average safety guarantees by examining how often and how severely safety bounds are violated, consistency across tasks and bounds, and the relationship between training-time and final policy behavior. It also proposes a safety tier system for categorizing algorithms and presents empirical safety evaluations on multiple navigation tasks. The authors recommend reporting aggregate metrics, distributional data, and task‑specific results together, and provide an open‑source suite, SafeRLEval, to facilitate reliable safety assessment.
arXiv:2601. 19612v3 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.
arXiv:2606. 31320v1 Announce Type: new Abstract: Safe online reinforcement learning requires policies to respect safety constraints while maintaining smooth optimization dynamics.