This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions (S-GMM-QFs). The framework reconciles streaming, non-stationary data with the Riemannian structure of the parameter space while handling distributional mismatch through experience replay.
arXiv:2512. 18763v2 Announce Type: replace Abstract: Unlike their conventional use as estimators of probability density functions in reinforcement learning (RL), this paper introduces a novel function-approximation role for Gaussian mixture models (GMMs) as direct surrogates for Q-function losses.
By Minh Vu, Konstantinos Slavakis
arXiv:2607. 10169v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities.
By Zhicheng Cai, Xinyuan Guo, Hanlin Wu, Mingxuan Wang, Wei-Ying Ma, Ya-Qin Zhang, Hao Zhou
arXiv:2606. 00350v1 Announce Type: cross Abstract: Offline reinforcement learning requires improving a policy from fixed data while avoiding out-of-distribution actions with unreliable value estimates.
By Anas Houssaini, Mohamad H. Danesh, Amin Abyaneh, Scott Fujimoto, Hsiu-Chin Lin, David Meger
arXiv:2606. 10613v1 Announce Type: cross Abstract: Diffusion-based Q-learning has emerged as a powerful paradigm for offline reinforcement learning, but its reliance on multi-step denoising makes both training and inference computationally expensive and brittle.
By Thanh Nguyen, Tri Ton, Hongbin Choe, Tung M. Luu, Chang D. Yoo
arXiv:2607. 21302v1 Announce Type: new Abstract: Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations.
By Gong Gao, Weidong Zhao, Xianhui Liu, Ning Jia