Genetic Reinforcement Learning for Neurocontrol Problems
Machine Learning - Special issue on genetic algorithms
Efficient reinforcement learning through symbiotic evolution
Machine Learning - Special issue on reinforcement learning
Differential Evolution Training Algorithm for Feed-Forward Neural Networks
Neural Processing Letters
Evolutionary adaptive-critic methods for reinforcement learning
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
JADE: adaptive differential evolution with optional external archive
IEEE Transactions on Evolutionary Computation
ICSI'11 Proceedings of the Second international conference on Advances in swarm intelligence - Volume Part I
Differential Evolution: A Survey of the State-of-the-Art
IEEE Transactions on Evolutionary Computation
A new evolutionary system for evolving artificial neural networks
IEEE Transactions on Neural Networks
Adaptive Learning and Control for MIMO System Based on Adaptive Dynamic Programming
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In this paper, we propose a novel strategy for approximating policy evaluation during online critic-actor learning procedure. We adopt the adaptive differential evolution with elites (ADEE) to optimize moving least square temporal difference with one step (MLSTD(0)) at the early stage which is good at global searching. Next we apply gradient method to perform local search efficiently and effectively. That solves the dilemma between explore and exploit in weight seeking for critic neural network. Simulation results on the online learning control of a cart pole benchmark demonstrate the efficiency of the presented method.