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.
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.
arXiv:2601. 22993v4 Announce Type: replace Abstract: We introduce Canary, a risk-averse method designed to optimize Value-at-Risk (VaR) constrained reinforcement learning (RL) problems.
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:2607. 15457v1 Announce Type: new Abstract: We study robust peak-cost constrained reinforcement learning (RP-CRL), where the objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory.
Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level stop-feedback: a binary signal at the first unsafe transition, with no per-step attribution. We frame this as a temporal credit assignment problem and propose the Redistribution-based Cost Inference (RCI) framework, which converts sparse stop-feedback into dense per-step costs via return decomposition, then trains a constrained offline policy on the augmented dataset.
arXiv:2608. 12306v1 Announce Type: cross Abstract: Safe offline RL typically assumes access to dense per-step cost annotations, but in practice supervisors provide only trajectory-level stop-feedback: a binary signal at the first unsafe transition, with no per-step attribution.