DocumentCode :
349959
Title :
Episode-based reinforcement learning-an instance-based approach for perceptual aliasing
Author :
Unemi, T. ; Saitoh, H.
Author_Institution :
Dept. of Inf. Syst. Sci., Soka Uuniv., Tokyo, Japan
Volume :
5
fYear :
1999
fDate :
1999
Firstpage :
435
Abstract :
Proposes a reinforcement learning method based on memorizing and retrieving episodes of the learner´s own experiences. The results of the computer simulation on a simple but typical non-Markovian environment is shown to clarify the performance. An instance-based reinforcement learning method previously proposed by Unemi (1992) is also based on the learner´s experiences memorized without any modification. But it is applicable only to the Markovian domain where it is enough for the learner to acquire a reactive policy to achieve the optimal behavior. An episode-based method not only overcomes perceptual aliasing but also inherits the advantages of the instance-based method on flexibility for applicable domains
Keywords :
learning (artificial intelligence); mobile robots; path planning; episode-based reinforcement learning; instance-based approach; learner´s experiences; nonMarkovian environment; perceptual aliasing; reactive policy; Computer simulation; Decision making; Information retrieval; Information systems; Learning systems; Nearest neighbor searches; Neural networks; Publishing; Robot sensing systems; Telecommunications;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
ISSN :
1062-922X
Print_ISBN :
0-7803-5731-0
Type :
conf
DOI :
10.1109/ICSMC.1999.815590
Filename :
815590
Link To Document :
بازگشت