| Presentation | 2003/10/16 On the Typical Sequence in Reinforcement Learning Kazunori IWATA, Kazushi IKEDA, Hideaki SAKAI, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we show the asymptotic equipartition property on the empirical sequences in reinforcement learning. This states that if the number of time steps is sufficiently large, then the typical set of empirical sequences has probability nearly one, all elements of the typical set are nearly equiprobable, and the size of the typical set is the exponential function of the conditional entropy. The property is very useful to analyze the reinforcement learning process. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Reinforcement Learning / Type Theory / Typical Sequence / Asymptotic Equipartition Property |
| Paper # | PRMU2003-123,NC2003-54 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2003/10/16(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 | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | On the Typical Sequence in Reinforcement Learning |
| Sub Title (in English) | |
| Keyword(1) | Reinforcement Learning |
| Keyword(2) | Type Theory |
| Keyword(3) | Typical Sequence |
| Keyword(4) | Asymptotic Equipartition Property |
| 1st Author's Name | Kazunori IWATA |
| 1st Author's Affiliation | Department of Systems Science, Graduate School of Informatics, Kyoto University() |
| 2nd Author's Name | Kazushi IKEDA |
| 2nd Author's Affiliation | Department of Systems Science, Graduate School of Informatics, Kyoto University |
| 3rd Author's Name | Hideaki SAKAI |
| 3rd Author's Affiliation | Department of Systems Science, Graduate School of Informatics, Kyoto University |
| Date | 2003/10/16 |
| Paper # | PRMU2003-123,NC2003-54 |
| Volume (vol) | vol.103 |
| Number (no) | 391 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |