The need for improved reinforcement learning techniques in intelligent agents

Author

Wunsch, Donald ; Prokhorov, Danil

Author_Institution

Dept. of Electr. Eng., Texas Tech. Univ., Lubbock, TX, USA

Volume

4

fYear

1997

fDate

12-15 Oct 1997

Firstpage

3073

Abstract

Reinforcement learning is an integral part of intelligent agent research. The development of this field, however, has been largely independent of the latest developments in neural networks. As a result, the most popular designs for intelligent agents utilize neural network architectures from several years ago. The article recommends newer, proven designs for reinforcement learning. The recommended designs share historical roots with the most popular architectures in place today, allowing improved performance without radical redesign of existing agents

Keywords

adaptive systems; dynamic programming; learning (artificial intelligence); neural nets; adaptive critic designs; critic net; dynamic programming; improved reinforcement learning techniques; intelligent agent research; neural network architectures; Computational intelligence; Computer networks; Cost function; Dynamic programming; Equations; Intelligent agent; Laboratories; Machine learning; Neural networks; Technological innovation;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on

Conference_Location

Orlando, FL

ISSN

1062-922X

Print_ISBN

0-7803-4053-1

Type

conf

DOI

10.1109/ICSMC.1997.633059

Filename

633059