Faster Fixed-Point Methods for Multichain MDPs

arXiv:2506.20910v2 Announce Type: replace-cross Abstract: We study value-iteration (VI) algorithms for solving general (a.k.a. multichain) Markov decision processes (MDPs) under the average-reward criterion, a fundamental but theoretically challenging setting. Beyond the difficulties inherent to all average-reward problems posed by the lack of contractivity and non-uniqueness of solutions to the Bellman operator, in the multichain setting an optimal policy must solve the navigation subproblem of steering towards the best connected component, in addition to optimizing long-run performance within each component. We develop algorithms which better solve this navigational subproblem in order to achieve faster convergence for multichain MDPs, obtaining improved rates of convergence and sharper measures of complexity relative to prior work. Many key components of our results are of potential independent interest, including novel connections between average-reward and discounted problems, optimal fixed-point methods for discounted VI which extend to general Banach spaces, new sublinear convergence rates for the discounted value error, and refined suboptimality decompositions for multichain MDPs. Overall our results yield faster convergence rates for discounted and average-reward problems and expand the theoretical foundations of VI approaches.

Related

• Policy Testing in Markov Decision Processes
• Beyond the Bellman Fixed Point: Geometry and Fast Policy Identification in Value Iteration
• On the Fundamental Limitations of Dual Static CVaR Decompositions in Markov Decision Processes
• MDP modeling for multi-stage stochastic programs
• MDP Planning as Policy Inference

Source: arXiv cs.LG | 2026-04-23