arXiv Machine Learning August 11, 2026 By Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb

Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2608. 07725v1 Announce Type: new Abstract: Average-reward reinforcement-learning regret is known up to logarithmic factors, but the numerical content of published guarantees is difficult to compare because probability mode, structural parameter, logarithmic normalization, prior information, and planning assumptions differ.

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 Machine Learning.

arXiv Machine Learning

2d ago

Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation

arXiv:2609.39093v1 Announce Type: new Abstract: We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probabi...

By Kihyun Yu, Seoungbin Bae, Dabeen Lee

reinforcement-learning

Hugging Face Trending Papers

3d ago

Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation

We study infinite-horizon average-reward constrained Markov decision processes (CMDPs) under the weakly communicating assumption. Existing high-probability guarantees for this setting either require c...

reinforcement-learning

arXiv Machine Learning

5d ago

Learning Chance-Constrained MDPs with Bellman Distributional Certificates

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

reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 23

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

arXiv:2607. 19854v1 Announce Type: new Abstract: We study horizon-free regret minimization for finite-horizon time-homogeneous tabular Markov decision processes with $S$ states, $A$ actions, horizon $H$, and per-trajectory total reward bounded by $1$.

By Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du

reinforcement-learning

arXiv Machine Learning

2d ago

Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback

arXiv:2609.38938v1 Announce Type: new Abstract: Reinforcement learning with human feedback (RLHF) learns from human comparisons, which can be corrupted or deliberately manipulated. This paper studies...

By Xinyi Ni, Lifeng Lai

reinforcement-learning safety

arXiv Machine Learning

Sep 11

Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations

arXiv:2609. 10866v1 Announce Type: new Abstract: Reinforcement learning (RL) agents deployed in real-world environments are often vulnerable to adversarial perturbations in state observations, creating risks in safety-critical applications.

By Tong Li, Saunak Kumar Panda, Yisha Xiang

agents reinforcement-learning safety

One email a morning, machine-written

Related stories

Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation

Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation

Learning Chance-Constrained MDPs with Bellman Distributional Certificates

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence

Robust Risk-Sensitive Reinforcement Learning from Corrupted Human Feedback

Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbations