The paper introduces Policy Gradient Penalty (PGP), a single‑loop policy‑space method that enforces convex occupancy‑measure constraints via quadratic‑penalty regularization. PGP constructs pseudo‑rewards to estimate gradients of the penalized objective and uses the classical Policy Gradient Theorem, establishing smoothness and global last‑iterate convergence guarantees for an ε‑optimal constrained entropy value with ε‑bounded constraint violation. The authors validate PGP with ablations on a grid‑world benchmark and demonstrate scalability on two challenging continuous‑control tasks.
By Florian Wolf, Ilyas Fatkhullin, Niao He
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.
By Shilpa Mukhopadhyay, Sourav Ganguly, Santosh Mohan Rajkumar, Honghao Wei, Debdipta Goswami, Arnob Ghosh
arXiv:2603. 09344v3 Announce Type: replace Abstract: Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift.
By Hongqiang Lin, Zhenghui Fu, Weihao Tang, Pengfei Wang, Yiding Sun, Qixian Huang, Dongxu Zhang
arXiv:2608. 01151v1 Announce Type: cross Abstract: In this paper, we consider stochastic optimal control problems with infinite-horizon joint chance constraints.
By Francesco Cordiano, Kanghui He, Bart De Schutter
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:2506. 07040v4 Announce Type: replace-cross Abstract: We study model-free methods for distributionally robust infinite-horizon average-reward Markov decision processes (MDPs).
By Yang Xu, Swetha Ganesh, Vaneet Aggarwal
arXiv:2607. 06935v1 Announce Type: cross Abstract: Reinforcement learning (RL) is increasingly grounded in tools from probability, optimization, and operator theory.
By Denis Belomestny, Alexander Gasnikov, Egor Gladin, Alexey Naumov, Artemy Rubtsov, Yuri Sapronov, Daniil Tiapkin, Nikita Yudin
arXiv:2602. 03778v2 Announce Type: replace-cross Abstract: Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-critical applications to prevent rare, yet catastrophic events.
By Aneri Muni, Vincent Taboga, Esther Derman, Pierre-Luc Bacon, Erick Delage
arXiv:2604. 26360v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy.
By Disha Singha
arXiv:2608. 10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints.
By Chenhua Fan, Jiahui Zhu, Yuhang Zhang, Honghao Wei
The paper introduces a new approach to learning chance-constrained Markov decision processes (CCMDPs) using a Bellman distributional certificate. It provides both model-based and model-free algorithms with theoretical guarantees, including matching upper and lower bounds for tabular discounted CCMDPs with bounded successor support. Numerical experiments on synthetic CCMDPs and an IEEE 14-bus energy storage benchmark demonstrate the safety and effectiveness of the proposed methods.
By Chenbei Lu, Hongyu Yi
The paper introduces robust successor features, a method that extends the successor representation to handle uncertainty in both reward functions and transition kernels within linear Markov Decision Processes. It provides a theoretical bound on Generalized Policy Improvement that quantifies performance loss due to mismatched dynamics, and demonstrates the approach on grid-based benchmarks against prior methods that consider only reward or transition differences.
By Erik Nikulski, Yamen Habib, Vicen\c{c} Gomez, Anders Jonsson, Rub\'en Moreno-Bote, Javier Segovia-Aguas