Evolutionary adaptive-critic methods for reinforcement learning

Authors:
Xin Xu;Han-gen He;Dewen Hu
Affiliations:
Dept. of Autom. Control, Nat. Univ. of Defense Technol., Changsha, China;Dept. of Autom. Control, Nat. Univ. of Defense Technol., Changsha, China;Dept. of Autom. Control, Nat. Univ. of Defense Technol., Changsha, China
Venue:
CEC '02 Proceedings of the Evolutionary Computation on 2002. CEC '02. Proceedings of the 2002 Congress - Volume 02
Year:
2002

Citing 0
Cited 2

A theoretical model and convergence analysis of memetic evolutionary algorithms

ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part II
A hybrid evolving and gradient strategy for approximating policy evaluation on online critic-actor learning

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel hybrid learning method is proposed for reinforcement learning problems with continuous state and action spaces. The reinforcement learning problems are modeled as Markov decision processes (MDPs) and the hybrid learning method combines evolutionary algorithms with gradient-based adaptive heuristic critic (AHC) algorithms to approximate the optimal policy of MDPs. The suggested method takes the advantages of evolutionary learning and gradient-based reinforcement learning to solve reinforcement learning problems. Simulation results on the learning control of an acrobot illustrate the efficiency of the presented method.