An incremental off-policy search in a model-free Markov decision process using a single sample path
Crossref DOI link: https://doi.org/10.1007/s10994-018-5697-1
Published Online: 2018-02-13
Published Print: 2018-06
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Joseph, Ajin George
Bhatnagar, Shalabh
Text and Data Mining valid from 2018-02-13
Article History
Received: 4 October 2016
Accepted: 27 January 2018
First Online: 13 February 2018