Non-asymptotic convergence analysis of Adam-type reinforcement learning algorithms under Markovian sampling (Conference Paper) | NSF PAGES

skip to main content

Citation Details

Non-asymptotic convergence analysis of Adam-type reinforcement learning algorithms under Markovian sampling

Award ID(s):: 1761506 1900145

NSF-PAR ID:: 10288066

Author(s) / Creator(s):: Qiong, H; Xu, T; Liang, Y; Zhang, W.

Date Published:: 2021-01-01

Journal Name:: Proc. AAAI Conference on Artificial Intelligence (AAAI)

Format(s):: Medium: X

Sponsoring Org:: National Science Foundation

Free Publicly Accessible Full Text
Accepted Manuscript1.0
Conference Paper:
The DOI is not currently available.