2000 character limit reached
On Value Iteration Convergence in Connected MDPs (2406.09592v1)
Published 13 Jun 2024 in cs.LG
Abstract: This paper establishes that an MDP with a unique optimal policy and ergodic associated transition matrix ensures the convergence of various versions of the Value Iteration algorithm at a geometric rate that exceeds the discount factor {\gamma} for both discounted and average-reward criteria.