Journal of System Simulation
Abstract
Abstract: Evolutionary reinforcement learning currently suffers from low sample efficiency, a single coupling method, and poor convergence, which can affect its performance and scaling. To address this issue, an improved algorithm based on elite gradient instruction and double random search was proposed. The direction of the reinforcement strategy gradient update was corrected by introducing elite strategy gradient guidance carrying evolutionary information during reinforcement strategy training. Double stochastic search was used to replace the original evolutionary component, reducing the complexity of the algorithm while making the policy search meaningful and controllable in the parameter space. The introduction of complete replacement information trading effectively balanced the learning and search of reinforcement and evolutionary strategies. Experimental results show that the method has improved exploration power, robustness, and convergence compared to the classical evolutionary reinforcement learning method.
Recommended Citation
Di, Jian; Wan, Xue; and Jiang, Limei
(2025)
"Evolutionary Reinforcement Learning Based on Elite Instruction and Random Search,"
Journal of System Simulation: Vol. 37:
Iss.
11, Article 15.
DOI: 10.16182/j.issn1004731x.joss.24-0604
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol37/iss11/15
First Page
2877
Last Page
2887
CLC
TP399
Recommended Citation
Di Jian, Wan Xue, Jiang Limei. Evolutionary Reinforcement Learning Based on Elite Instruction and Random Search[J]. Journal of System Simulation, 2025, 37(11): 2877-2887.
DOI
10.16182/j.issn1004731x.joss.24-0604
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons