Presentation | 2004/3/12 Efficiency Improvement of Reinforcement Learning by Sensory Information Keiji KAMEI, Masumi ISHIKAWA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Mobile robots severely suffer from slow learning speed of reinforcement learning. To overcome this difficulty, we propose a method for improving its learning efficiency by directly updating a value function based on sensory information. Computer simulation demonstrates the effectiveness of the proposed method; the number of goals reached is about two times larger than that by conventional reinforcement learning in the beginning stage of learning. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | reinforcement learning / sensory information / mobile robot / optimal pass |
Paper # | NC2003-207 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2004/3/12(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) | Efficiency Improvement of Reinforcement Learning by Sensory Information |
Sub Title (in English) | |
Keyword(1) | reinforcement learning |
Keyword(2) | sensory information |
Keyword(3) | mobile robot |
Keyword(4) | optimal pass |
1st Author's Name | Keiji KAMEI |
1st Author's Affiliation | Graduate School of Life Science and Systems and Engneering, Kyushu Institute of Technology() |
2nd Author's Name | Masumi ISHIKAWA |
2nd Author's Affiliation | Graduate School of Life Science and Systems and Engneering, Kyushu Institute of Technology |
Date | 2004/3/12 |
Paper # | NC2003-207 |
Volume (vol) | vol.103 |
Number (no) | 734 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |