Presentation | 2006-07-04 Feature Space Construction and Function Approximation for Reinforcement Learning Hideki SATOH, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A feature space construction method for function approximation was developed and applied to reinforcement learning for multi-dimensional continuous state spaces. First, a non-linear function was approximated using a linear combination of elements of a basis. Next, the elements with small-absolute-value corresponding coefficients were replaced with other candidate elements. Making this replacement at periodic intervals resulted in the basis constructing an optimum feature space for function approximation. An example chaos control problem for multiple logistic maps was solved, demonstrating that reinforcement learning with feature space construction can not only construct an optimum feature space with the minimum degree of expansion but also reconstruct an optimum feature space based on changes in the environment. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | feature space / function approximation / non-linear / reinforcement learning / multi-dimensional |
Paper # | NLP2006-41 |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2006/6/27(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Nonlinear Problems (NLP) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Feature Space Construction and Function Approximation for Reinforcement Learning |
Sub Title (in English) | |
Keyword(1) | feature space |
Keyword(2) | function approximation |
Keyword(3) | non-linear |
Keyword(4) | reinforcement learning |
Keyword(5) | multi-dimensional |
1st Author's Name | Hideki SATOH |
1st Author's Affiliation | School of Systems Information Science, Future University-Hakodate() |
Date | 2006-07-04 |
Paper # | NLP2006-41 |
Volume (vol) | vol.106 |
Number (no) | 136 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |