Windows deep transformer Q-networks: an extended variance reduction architecture for partially observable reinforcement learning
Crossref DOI link: https://doi.org/10.1007/s10489-024-05867-3
Published Online: 2024-11-27
Published Print: 2025-01
Update policy: https://doi.org/10.1007/springer_crossmark_policy
Wang, Zijian
Wang, Bin https://orcid.org/0000-0002-0092-3951
Dou, Hongbo
Liu, Zhongyuan
Text and Data Mining valid from 2024-11-27
Version of Record valid from 2024-11-27
Article History
Accepted: 6 November 2024
First Online: 27 November 2024
Declarations
:
: The authors declare that there is no conflict of interest.
: Not applicable.