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
arXiv:2404. 03578v3 Announce Type: replace Abstract: The sim-to-real gap, which represents the disparity between training and testing environments, poses a significant challenge in reinforcement learning (RL).
By Miao Lu, Han Zhong, Tong Zhang, Jose Blanchet
arXiv:2607. 20822v1 Announce Type: new Abstract: Motivated by reinforcement learning in harsh environments, we consider the problem of learning an optimal policy subject to adversarially corrupted feedback.
By Sreejeet Maity, Aritra Mitra
The paper introduces TriTrust-PBRL (TTP), a framework for preference-based reinforcement learning that learns a shared reward model and expert-specific trust parameters from multi-expert feedback. Trust parameters evolve to be positive (trust), near zero (ignore), or negative (flip), allowing the model to invert adversarial preferences instead of discarding them. Experiments on manipulation and locomotion tasks show TTP achieves near-oracle performance under adversarial corruption, outperforming existing PBRL methods.
By Seyed Amir Hosseini, Maryam Abdolali, Amirhosein Tavakkoli, Fardin Ayar, Ehsan Javanmardi, Manabu Tsukada, Mahdi Javanmardi
arXiv:2606. 30923v1 Announce Type: cross Abstract: Imitation Learning is a natural framework for learning in sequential decision-making systems and has emerged as the dominant paradigm through which we understand language model training.
By Ved Sriraman, Peihan Liu, Daniel Hsu, Adam Block
arXiv:2503. 00539v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) has evolved to be one of the main methods for fine-tuning large language models (LLMs).
By Debmalya Mandal, Paulius Sasnauskas, Goran Radanovic
arXiv:2506. 06891v3 Announce Type: replace Abstract: We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al.
By Paulius Sasnauskas, Yi\u{g}it Yal{\i}n, Goran Radanovi\'c
arXiv:2607. 02288v1 Announce Type: cross Abstract: While pessimism counteracts overestimation bias in offline reinforcement learning (RL), being overly conservative has been associated with hindering certain forms of generalization.
By Max Weltevrede, Matthijs T. J. Spaan, Wendelin B\"ohmer
arXiv:2605. 00155v3 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) is a central post-training tool for aligning large language models, but its training reward is only a learned proxy for true human utility.
By Yikai Wang, Shang Liu, Jose Blanchet
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:2604. 10062v3 Announce Type: replace Abstract: We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives.
By Jose Efraim Aguilar Escamilla, Haoyang Hong, Jiawei Li, Haoyu Zhao, Xuezhou Zhang, Sanghyun Hong, Huazheng Wang
arXiv:2607. 14180v1 Announce Type: cross Abstract: World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset.
By Logan Mondal Bhamidipaty, Mykel Kochenderfer, Subramanian Ramamoorthy