Presentation | 2007-12-22 Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation Hirotaka HACHIYA, Takayuki AKIYAMA, Masashi SUGIYAMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Off-policy reinforcement learning is aimed at efficiently reusing data samples gathered in the past. A common approach is to use importance sampling techniques for compensating for the bias caused by the difference between data-collecting policies and the target policy. However, existing off-policy methods do not often take the variance of value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a statistical machine learning theory. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Off-policy Reinforcement learning / Value function approximation / Importance sampling |
Paper # | NC2007-84 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2007/12/15(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 | Neurocomputing (NC) |
---|---|
Language | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation |
Sub Title (in English) | |
Keyword(1) | Off-policy Reinforcement learning |
Keyword(2) | Value function approximation |
Keyword(3) | Importance sampling |
1st Author's Name | Hirotaka HACHIYA |
1st Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology() |
2nd Author's Name | Takayuki AKIYAMA |
2nd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
3rd Author's Name | Masashi SUGIYAMA |
3rd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology |
Date | 2007-12-22 |
Paper # | NC2007-84 |
Volume (vol) | vol.107 |
Number (no) | 410 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |