Towards robust model-based reinforcement learning against adversarial corruption

[PDF] arxiv.org

Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm

M Lu, H Zhong, T Zhang, J Blanchet - arXiv preprint arXiv:2404.03578, 2024 - arxiv.org
The sim-to-real gap, which represents the disparity between training and testing
environments, poses a significant challenge in reinforcement learning (RL). A promising …
被引用次数：4 相关文章 所有 3 个版本
[PDF] arxiv.org

Robust Decision Transformer: Tackling Data Corruption in Offline RL via Sequence Modeling

J Xu, R Yang, F Luo, M Fang, B Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Learning policies from offline datasets through offline reinforcement learning (RL) holds
promise for scaling data-driven decision-making and avoiding unsafe and costly online …
相关文章 所有 2 个版本
[PDF] arxiv.org

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF

H Zhao, C Ye, Q Gu, T Zhang - arXiv preprint arXiv:2411.04625, 2024 - arxiv.org
Reverse-Kullback-Leibler (KL) regularization has emerged to be a predominant technique
used to enhance policy optimization in reinforcement learning (RL) and reinforcement …
相关文章 所有 3 个版本