期刊论文

Wong, KKL

英文

Entropy

1099-4300

2022

24

4

440-

10.3390/e24040440

Data curation, S.L.; Funding acquisition, W.C.; Methodology, K.K.L.W.; Resources, Z.S.; Writing—review & editing, W.C. All authors have read and agreed to the published version of the manuscript. This work was supported in part by the National Natural Science Foundation of China under Grant 61672540; in part by the Project of General University Teaching Reform Research in Hunan Province under Grant [2017]352.

本校为第一且通讯机构

In the field of reinforcement learning, we propose a Correct Proximal Policy Optimization (CPPO) algorithm based on the modified penalty factor β and relative entropy in order to solve the robustness and stationarity of traditional algorithms. Firstly, In the process of reinforcement learning, this paper establishes a strategy evaluation mechanism through the policy distribution function. Secondly, the state space function is quantified by introducing entropy, whereby the approximation policy is used to approximate the real policy distribution...