The paper proves that using a permissive safety filter in reinforcement learning does not compromise asymptotic performance. By formalizing safety through a safety‑critical Markov decision process and a filtered MDP, the authors show that optimal policies in the filtered MDP achieve the same return as the best safe policy in the original setting. Experiments on Safety Gymnasium confirm zero violations during training and performance that matches or exceeds unfiltered baselines.
By Donggeon David Oh, Duy P. Nguyen, Haimin Hu, Jaime Fern\'andez Fisac
The paper introduces a new approach to safety in contextual bandits with continuous actions, focusing on high‑probability constraints on the realized cost rather than expected cost. It presents the High‑Probability Constrained UCB algorithm, which balances reward exploration with conservative safety estimation, and provides theoretical regret guarantees for linear models and extensions to general function classes. Experiments demonstrate that this realized‑cost safety framework significantly reduces safety violations compared to expected‑cost constrained methods.
By Spyros Dragazis, Aldo Pacchiano
arXiv:2609. 12014v1 Announce Type: new Abstract: Safe offline reinforcement learning assumes a cost function on every transition.
By Adam Haroon, Cody Fleming
arXiv:2606. 15385v1 Announce Type: new Abstract: Reward hacking, where AI systems exploit misspecified objectives to achieve high reward without satisfying intended goals, remains a central challenge in AI safety.
By \"Omer Veysel \c{C}a\u{g}atan, Xuandong Zhao
arXiv:2604. 10727v2 Announce Type: replace-cross Abstract: Classical information-theoretic learning bounds typically rely on KL mutual information and moment-generating-function (MGF) arguments, which are well matched to bounded or sub-Gaussian losses but can be ineffective when losses or rewards are heavy-tailed.
By Huiming Zhang, Binghan Li, Wan Tian, Qiang Sun
The paper introduces Exchange Policy Optimization (EPO), a framework for semi‑infinite safe reinforcement learning that handles infinitely many constraints by iteratively solving finite subproblems. EPO expands or deletes constraints based on tolerance violations and Lagrange multipliers, maintaining computational tractability while converging to an optimal policy with bounded safety violations. The authors prove finite convergence, provide iteration bounds, and quantify the suboptimality gap under mild assumptions.
By Jiaming Zhang, Yujie Yang, Haoning Wang, Liping Zhang, Shengbo Eben Li
arXiv:2606. 04812v1 Announce Type: cross Abstract: Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep RL may demonstrate susceptibility to transition perturbations that result in unknown or unsafe behaviour.
By Mohit Prashant, Arvind Easwaran
The paper introduces a new approach to safety in contextual bandits with continuous actions by enforcing high‑probability constraints on the realized cost rather than on its expectation. It proposes the High‑Probability Constrained UCB algorithm, which balances optimistic reward exploration with pessimistic safety estimation. The authors provide theoretical regret guarantees for linear models and extend the analysis to general function classes, demonstrating experimentally that realized‑cost constraints significantly reduce safety violations compared to expected‑cost baselines.
arXiv:2609.06036v1 Announce Type: new
Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box \emph{generators}---are increasingly deployed behind runtim...
By Guangxi Wan, Yongbo Xie, Yuqi Liu, Qingwei Dong, Qingxin Li, Hongfei Bai, Peng Zeng
arXiv:2602.04125v2 Announce Type: replace-cross
Abstract: Modern digital platforms use contextual bandits to allocate valuable exposure and opportunities among competing participants. Fair treatment...
By Qingwen Zhang, Wenjia Wang
The paper introduces a chance-constrained approach to fine‑tune large language models (LLMs) that limits the proportion of safety examples whose performance degrades beyond a set threshold relative to a reference model. By replacing the discontinuous violation indicator with a differentiable majorization, the authors derive a tractable, conservative constraint and a closed‑form, constraint‑aware gradient update that focuses on examples near or above the degradation threshold. Experiments on harmful fine‑tuning across three tasks and models show that this tail‑aware method consistently outperforms existing safety‑preserving baselines, suggesting that safety preservation should be treated as a reliability‑constrained optimization problem rather than average‑risk regularization.
By Taha Entesari, Mahyar Fazlyab
arXiv:2603. 13356v2 Announce Type: replace Abstract: Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget.
By Majid Ghasemi, Mark Crowley