The paper presents the first provably efficient offline reinforcement learning algorithms for risk-sensitive settings using optimized certainty equivalents (OCE). It introduces two formulations—dynamic-OCE, applying OCE at each step, and static-OCE, applying a single OCE to cumulative rewards—and develops pessimistic value-iteration methods with tight sublinear suboptimality bounds in tabular and linear function approximation settings. The authors also establish minimax lower bounds, characterizing the fundamental limits of offline risk-sensitive RL.
arXiv:2510. 19528v2 Announce Type: replace-cross Abstract: We investigate the fundamental problem of leveraging offline data to accelerate online reinforcement learning - a direction with strong potential but limited theoretical grounding.
arXiv:2606. 18531v1 Announce Type: cross Abstract: Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets record only trajectory-level outcomes.
arXiv:2608. 03562v1 Announce Type: new Abstract: Reinforcement learning (RL) with general utility extends classic RL by optimizing an arbitrary utility functional of the policy-induced occupancy measure, thereby enabling a broader range of applications.
arXiv:2608. 01151v1 Announce Type: cross Abstract: In this paper, we consider stochastic optimal control problems with infinite-horizon joint chance constraints.
The paper introduces WSP-CVaR-RLHF, a risk‑sensitive reinforcement learning algorithm that learns from human feedback while handling corrupted or adversarial preference labels. It uses uncertainty‑weighted reward estimation and optimistic CVaR planning to achieve a regret bound that separates clean statistical cost from corruption penalties. Experiments with four adversarial attacks show that the method consistently reduces cumulative regret compared to an unweighted robust baseline while maintaining confidence‑set coverage.
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.
arXiv:2604. 06039v2 Announce Type: replace-cross Abstract: Value iteration-type methods have been extensively studied for computing a nearly optimal value function in reinforcement learning (RL).
arXiv:2610.08384v1 Announce Type: new Abstract: In this work, we consider decision-focused learning (DFL) for a Markov decision process (MDP), where existing methods differentiate through the KKT con...
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.
In this work, we consider decision-focused learning (DFL) for a Markov decision process (MDP), where existing methods differentiate through the KKT conditions of the Bellman equation and require solvi...
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.
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.