Variance reduced value iteration and faster algorithms for solving Markov decision processes

Aaron Sidford, Mengdi Wang, Xian Wu, Yinyu Ye

Research output: Contribution to journalArticlepeer-review


In this paper we provide faster algorithms for approximately solving discounted Markov decision processes in multiple parameter regimes. Given a discounted Markov decision process (DMDP) with |S| states, |A| actions, discount factor γ ∈ (0, 1), and rewards in the range [−M, M], we show how to compute an ϵ-optimal policy, with probability 1 − δ in time (Note: We use (Figure presented.) to hide polylogarithmic factors in the input parameters, that is, (Figure presented.).) (Figure presented.) This contribution reflects the first nearly linear time, nearly linearly convergent algorithm for solving DMDPs for intermediate values of γ. We also show how to obtain improved sublinear time algorithms provided we can sample from the transition function in O(1) time. Under this assumption we provide an algorithm which computes an ϵ-optimal policy for (Figure presented.) with probability 1 − δ in time (Figure presented.) Furthermore, we extend both these algorithms to solve finite horizon MDPs. Our algorithms improve upon the previous best for approximately computing optimal policies for fixed-horizon MDPs in multiple parameter regimes. Interestingly, we obtain our results by a careful modification of approximate value iteration. We show how to combine classic approximate value iteration analysis with new techniques in variance reduction. Our fastest algorithms leverage further insights to ensure that our algorithms make monotonic progress towards the optimal value. This paper is one of few instances in using sampling to obtain a linearly convergent linear programming algorithm and we hope that the analysis may be useful more broadly.

Original languageEnglish (US)
Pages (from-to)423-442
Number of pages20
JournalNaval Research Logistics
Issue number5
StatePublished - Aug 2023

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Ocean Engineering
  • Management Science and Operations Research


  • Markov decision processes
  • linear programming algorithm
  • value iteration


Dive into the research topics of 'Variance reduced value iteration and faster algorithms for solving Markov decision processes'. Together they form a unique fingerprint.

Cite this