Jul 2026
A Unified Algorithmic Framework for Hybrid Reinforcement Learning in Tabular MDPs with Shifted Transition Dynamics
A unified algorithmic framework featuring two algorithms: MIN-UCB-VI for regret minimization and MAX-LCB-VI for best policy identification for best policy identification is proposed, including both instance-dependent and independent upper bounds on regret and sub-optimality gap.
Zhe-Shun Wu, Renjie Zheng, Jinhang Zuo et al.
· arXiv.org · 1 citation