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:2608. 08491v1 Announce Type: new Abstract: Reward models are a bottleneck for reinforcement learning in embodied AI.
By Yidong Wang, Yan Zhan, Ziteng Feng, Zhenyu Cui, Ziyi Zhou, Renzhao Liang, Jiaxuan Zhu, Zilei Yang, Yiran Zhao, Zhongkuan Mao, Bo Jia, Hanchu Ni, Chenggang Xie, Biao Liu, Yi Zhang, Yong Dai, Xiaozhu Ju, Wei Ye, Shikun Zhang
arXiv:2605. 11020v2 Announce Type: replace-cross Abstract: Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories.
By Anish Diwan, Davide Tateo, Christopher E. Mower, Haitham Bou-Ammar, Jan Peters, Oleg Arenz
arXiv:2610.17062v1 Announce Type: cross
Abstract: We propose a mitigation to reward hacking in reinforcement learning. Our setup involves a misspecified reward function that gives rise to unintended...
By Jake Ward, Shawn Hu, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud
The paper introduces Adversarial Importance Sampling (Advis), a technique that leverages importance sampling over standard training trajectories to estimate and optimize worst‑case returns without extra environment interactions or auxiliary networks, thereby capturing long‑term robustness. It also presents advrl, a modular PyTorch library that consolidates existing robustness methods and adversarial attacks into single‑file implementations for easier prototyping and reproducible evaluation. Finally, the authors highlight that optimal adversarial hyperparameters do not transfer across agents, prompting evaluation against a broader set of attackers (6–14× more configurations) and demonstrate the effectiveness of their approach on continuous control tasks.
By Amine Andam, Jamal Bentahar, Mustapha Hedabou
arXiv:2607. 03600v1 Announce Type: cross Abstract: Adversarial robustness in Unsupervised Domain Adaptation (UDA) remains a significant challenge due to noisy pseudo labels and inherent distributional shifts between the clean source and adversarially perturbed target domains.
By Sushant Dagaji Desale, Rahul Mishra, Ashutosh Kumar Sinha