Zhiyou Yang, Hong Qu, Mingsheng Fu, Wang Hu, Yongze Zhao. A Maximum Divergence Approach to Optimal Policy in Deep Reinforcement Learning. IEEE T. Cybernetics, 53(3):1499-1510, March 2023. [doi]
@article{YangQFHZ23,
title = {A Maximum Divergence Approach to Optimal Policy in Deep Reinforcement Learning},
author = {Zhiyou Yang and Hong Qu and Mingsheng Fu and Wang Hu and Yongze Zhao},
year = {2023},
month = {March},
doi = {10.1109/TCYB.2021.3104612},
url = {https://doi.org/10.1109/TCYB.2021.3104612},
researchr = {https://researchr.org/publication/YangQFHZ23},
cites = {0},
citedby = {0},
journal = {IEEE T. Cybernetics},
volume = {53},
number = {3},
pages = {1499-1510},
}