GEM: Guided Expectation-Maximization for Behavior-Normalized Candidate Action Selection in Offline RL

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Haoyu, Wang, Jingcheng, Wu, Shunyu, Xiao, Xinwei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!