Self-adjusting reinforcement learning

Authors: 
Der, Ralf
Herrmann, Michael
Year: 
1996
Language: 
English
Abstract: 
We present a variant of the Q-learning algorithm with automatic control of the exploration rate by a competition scheme. The theoretical approach is accompanied by systematic simulations of a chaos control task. Finally, we give interpretations of the algorithm in the context of computational ecology and neural networks.
Appeared / Erschienen in: 
Proc. Nonlinear Theory and Applications - NOLTA '96, S. 441-444, (Kochi, Japan, Oct.7-9, 1996)
Pubdate / Erscheinungsdatum: 
1996
Pages / Seitenanzahl: 
4
AttachmentSize
1996-22.pdf120.96 KB