Timezone: »

Corruption-Robust Algorithms with Uncertainty Weighting for Nonlinear Contextual Bandits and Markov Decision Processes
Chenlu Ye · Wei Xiong · Quanquan Gu · Tong Zhang

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #328
Despite the significant interest and progress in reinforcement learning (RL) problems with adversarial corruption, current works are either confined to the linear setting or lead to an undesired $\tilde{\mathcal O}(\sqrt{T}\zeta)$ regret bound, where $T$ is the number of rounds and $\zeta$ is the total amount of corruption. In this paper, we consider contextual bandits with general function approximation and propose a computationally efficient algorithm to achieve a regret of $\tilde{\mathcal O}(\sqrt{T}+\zeta)$. The proposed algorithm relies on the recently developed uncertainty-weighted least-squares regression from linear contextual bandits (He et al., 2022) and a new weighted estimator of uncertainty for the general function class. In contrast to the existing analysis for the sum of uncertainty that is heavily based on the linear structure, we develop a novel technique to control the sum of weighted uncertainty, thus establishing the final regret bound. We then generalize our algorithm to the episodic MDP and first achieve an additive dependence on the corruption level $\zeta$ in the scenario of general function approximation. Notably, our algorithms achieve regret bounds that either nearly match the lower bound or improve the performance of existing methods for all the corruption levels in both known and unknown $\zeta$ cases.

Author Information

Chenlu Ye (The Hong Kong University of Science and Technology)

I am now a Ph.D.student who has strong interest in machine learning, especially machine learning theory.

Wei Xiong (The Hong Kong University of Science and Technology)
Quanquan Gu (University of California, Los Angeles)
Tong Zhang (HKUST)
Tong Zhang

Tong Zhang is a professor of Computer Science and Mathematics at the Hong Kong University of Science and Technology. His research interests are machine learning, big data and their applications. He obtained a BA in Mathematics and Computer Science from Cornell University, and a PhD in Computer Science from Stanford University. Before joining HKUST, Tong Zhang was a professor at Rutgers University, and worked previously at IBM, Yahoo as research scientists, Baidu as the director of Big Data Lab, and Tencent as the founding director of AI Lab. Tong Zhang was an ASA fellow and IMS fellow, and has served as the chair or area-chair in major machine learning conferences such as NIPS, ICML, and COLT, and has served as associate editors in top machine learning journals such as PAMI, JMLR, and Machine Learning Journal.

More from the Same Authors