A Neural Network-Based Policy Iteration Algorithm with Global $$H^2$$-Superlinear Convergence for Stochastic Games on Domains
Crossref DOI link: https://doi.org/10.1007/s10208-020-09460-1
Published Online: 2020-05-18
Published Print: 2021-04
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Ito, Kazufumi
Reisinger, Christoph
Zhang, Yufei
Funding for this research was provided by:
University of Oxford
Text and Data Mining valid from 2020-05-18
Version of Record valid from 2020-05-18
Article History
Received: 14 June 2019
Revised: 23 January 2020
Accepted: 30 March 2020
First Online: 18 May 2020