Haoyang Hong

Oregon State University

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Training Efficiency & Optimization (1)World Models & Planning (1)

Frequent co-authors

Zichen Wang (1)Quanquan Gu (1)Huazheng Wang (1)

Papers (1)

Jun 4, 2026

Jun 4, 2026·also Univer- sity of Illinois, University of California

Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification

KL-regularization can still yield high-probability guarantees even when models are misspecified, challenging the assumption that realizability is necessary for effective learning.

Haoyang Hong, Zichen Wang, Quanquan Gu +1

Training Efficiency & Optimization World Models & Planning

Search

Haoyang Hong

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)