AE-RTG: An Action Exploration Agent for Offline Reinforcement Learning Based on Returns-To-Go Regularization

SSRN Electronic Journal 2026 Preprint Open access

Read full text

Authors: Jiazheng Wen, Junbao Li, Huanyu Liu

DOI: 10.2139/ssrn.6072137

Cited by: 0

Fields of Study & Subjects

Reinforcement Learning in Robotics Domain Adaptation and Few-Shot Learning Advanced Bandit Algorithms Research