Presentation | 2008-11-06 Reinforcement Learning for High-dimensional Action Space : Action Space Compression Based on Principal Component Analysis Hideki SATOH, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Adaptive basis construction, state space compression, and action space compression are used to extend reinforcement learning for controlling an environment with high-dimensional state and action spaces. First, an appropriate pre-controller determines actions in the original action space, and the statistics of the actions are measured. Next, the principal axis matrix of the actions is computed using principal component analysis. The original action space can be compressed using the principal axis matrix. The original state space is also compressed using state space compression based on reward-weighted principal component analysis, and an orthonormal basis is adaptively constructed using adaptive basis construction based on the activity-oriented index allocation. Finally, a main controller based on reinforcement learning determines an action in the compressed action space, and an action in the original action space is computed from the action in the compressed action space using the principal axis matrix. Computer simulation of routing problems showed that the reinforcement learning worked well and that the routing algorithm using it was robust. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | compression / function approximation / multivariate analysis / reinforcement learning / robust routing |
Paper # | NLP2008-64 |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2008/10/30(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) | Reinforcement Learning for High-dimensional Action Space : Action Space Compression Based on Principal Component Analysis |
Sub Title (in English) | |
Keyword(1) | compression |
Keyword(2) | function approximation |
Keyword(3) | multivariate analysis |
Keyword(4) | reinforcement learning |
Keyword(5) | robust routing |
1st Author's Name | Hideki SATOH |
1st Author's Affiliation | School of Systems Information Science, Future University-Hakodate() |
Date | 2008-11-06 |
Paper # | NLP2008-64 |
Volume (vol) | vol.108 |
Number (no) | 276 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |