摘要
The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social sciences.Seeking an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement learning.In this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical laws.We find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral rewards.We apply this finding to solve output-feedback design problems in power systems.The results reveal that our approach removes an intermediate stage of identifying dynamical models.Our work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.
基金
supported by the Guangdong Basic and Applied Basic Research Foundation(2024A1515011936)
the National Natural Science Foundation of China(62320106008)
作者简介
Corresponding author:Ci Chen,emails:ci.chen@gdut.edu.cn;Corresponding author:Lihua Xie,emails:elhxie@ntu.edu.sg;Corresponding author:Shengli Xie,emails:shlxie@gdut.edu.cn
