Skip to main navigation Skip to search Skip to main content

Asynchronous Value Iteration for Markov Decision Processes with Continuous State Spaces

  • Xiangyu Yang
  • , Jian Qiang Hu
  • , Jiaqiao Hu
  • , Yijie Peng
  • Fudan University
  • Peking University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

We propose a simulation-based value iteration algorithm for approximately solving infinite horizon discounted MDPs with continuous state spaces and finite actions. At each time step, the algorithm employs the shrinking ball method to estimate the value function at sampled states and uses historical estimates in an interpolation-based fitting strategy to build an approximator of the optimal value function. Under moderate conditions, we prove that the sequence of approximators generated by the algorithm converges uniformly to the optimal value function with probability one. Simple numerical examples are provided to compare our algorithm with two other existing methods.

Original languageEnglish
Title of host publicationProceedings of the 2020 Winter Simulation Conference, WSC 2020
EditorsK.-H. Bae, B. Feng, S. Kim, S. Lazarova-Molnar, Z. Zheng, T. Roeder, R. Thiesing
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2856-2866
Number of pages11
ISBN (Electronic)9781728194998
DOIs
StatePublished - Dec 14 2020
Event2020 Winter Simulation Conference, WSC 2020 - Orlando, United States
Duration: Dec 14 2020Dec 18 2020

Publication series

NameProceedings - Winter Simulation Conference
Volume2020-December
ISSN (Print)0891-7736

Conference

Conference2020 Winter Simulation Conference, WSC 2020
Country/TerritoryUnited States
CityOrlando
Period12/14/2012/18/20

Fingerprint

Dive into the research topics of 'Asynchronous Value Iteration for Markov Decision Processes with Continuous State Spaces'. Together they form a unique fingerprint.

Cite this