arXiv Machine Learning June 16, 2026 By Saptarshi Mandal, Yashaswini Murthy, R. Srikant

Finite-Time Convergence of Distributionally Robust Q-Learning with Linear Function Approximation

Read the original on arXiv Machine Learning →

arXiv:2510. 01721v3 Announce Type: replace Abstract: Distributionally robust reinforcement learning (DRRL) seeks policies that perform well when the deployment transition model differs from the nominal model generating the data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

reinforcement-learning

arXiv AI

Jul 14

Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning

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

reinforcement-learning

arXiv AI

Jun 18

Robust Regularized Policy Iteration under Transition Uncertainty

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

reinforcement-learning benchmarks

arXiv Machine Learning

Aug 5

Revisiting TD Target Aggregation under Uncertainty in Q-Learning

arXiv:2608. 03069v1 Announce Type: new Abstract: Deep Q-Networks (DQNs) learn value functions through bootstrapped temporal-difference updates, where future returns are approximated using a greedy maximization over next-state action values.

By Lipeng Zu, Xiaonan Zhang

reinforcement-learning benchmarks

arXiv AI

Jul 1

Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity

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

reinforcement-learning safety

arXiv AI

Jun 10

Geometrically Averaged Hard Target Updates for Linear Q-Learning

arXiv:2606. 10835v1 Announce Type: cross Abstract: Periodic hard target updates are among the most common stabilization devices in modern deep Q-learning.

By Donghwan Lee

reinforcement-learning

arXiv AI

Jun 3

Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics

arXiv:2606. 02645v1 Announce Type: cross Abstract: Periodic target updates in Q-learning and soft target updates in actor-critic methods are empirically well established stabilization mechanisms, but their precise theoretical explanation is still incomplete.

By Donghwan Lee

reinforcement-learning

Related stories

Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning

Robust Regularized Policy Iteration under Transition Uncertainty

Revisiting TD Target Aggregation under Uncertainty in Q-Learning

Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity

Geometrically Averaged Hard Target Updates for Linear Q-Learning

Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics