← Back to all news
arXiv AI By Hanzhen Wang, Boxiang Lyu, Zhongxiang Dai, Siyang Gao, Dake Zhang, Shuang Qiu

Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents

Read the original on arXiv AI →

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.

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.

Related stories

arXiv Machine Learning
Oct 2

Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback

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.

By Xinyi Ni, Lifeng Lai
reinforcement-learningsafety
More like this →