Presentation | 2002/12/6 A Driver Model based on Reinforcement Learning Switching Multiple Controllers Atsushi ORITA, Yasuharu KOIKE, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose a reinforcement learning architecture which switches multiple controllers and outputs continuous control commands. We used Q-learning for switching the controllers and Actor-Critic for controlling commands. This architecture was applied to a car following task in which speed and headway distance were controlled. The task includes the problem that which pedal and how much the following car step on. From simulation results, we confirmed that it could aquire the control method to achive the task. And we compared our model with one Actor-Critic model about the ability of the car following task. We also showed that the control method had the similar driving characteristic to drivers' one. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Reinforcement learning / Speed and headway distance control / Driver model |
Paper # | NC2002-100 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2002/12/6(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) | A Driver Model based on Reinforcement Learning Switching Multiple Controllers |
Sub Title (in English) | |
Keyword(1) | Reinforcement learning |
Keyword(2) | Speed and headway distance control |
Keyword(3) | Driver model |
1st Author's Name | Atsushi ORITA |
1st Author's Affiliation | Department of Computational Intelligence and Systems Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology() |
2nd Author's Name | Yasuharu KOIKE |
2nd Author's Affiliation | JST PRESTO:Precision and Intelligence Laboratory, Tokyo Institute of Technology |
Date | 2002/12/6 |
Paper # | NC2002-100 |
Volume (vol) | vol.102 |
Number (no) | 508 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |