Crossmark

An offline-to-online reinforcement learning approach based on multi-action evaluation with policy extension

Published Online: 2024-09-11

Published Print: 2024-12

Authors

Cheng, Xuebo

Huang, Xiaohui https://orcid.org/0000-0001-7269-4484
Huang, Zhichao

Jiang, Nan
Funding

Funding for this research was provided by:

Innovative Research Group Project of the National Natural Science Foundation of China (62062033)

Natural Science Foundation of Jiangxi Province (20232BAB202018)
License Information

Text and Data Mining valid from 2024-09-11

Version of Record valid from 2024-09-11
More Information

Article History

Accepted: 22 August 2024

First Online: 11 September 2024

Declarations

:

: Relevant ethical guidelines and regulations were followed in conducting this study.

: The authors declare that there are no potential competing interests or conflicting relationships in this study.

Document is current