A data-based online reinforcement learning algorithm satisfying probably approximately correct principle
Crossref DOI link: https://doi.org/10.1007/s00521-014-1738-2
Published Online: 2014-10-30
Published Print: 2015-05
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Zhu, Yuanheng
Zhao, Dongbin
Text and Data Mining valid from 2014-10-30