| Presentation | 2002/3/11 Behavior acquisition for a real robot with a visual sensor by Direct-Vision-Based Reinforcent Learning Masaru IIDA, Masanori SUGISAKA, Katsunari SHIBATA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper it is verified that Direct-Vision-Based Reinforcement Learning(RL) is effective in on-line action learning of a real mobile robot with a linear monochrome visual sensor. In Direct-Vision-Based RL, row visual sensory signals are put into a layered neural network directly, and the neural network is trained by Back Propagation using the training signal generated based on reinfbrcement learning. It was confirmed that the robot could obtain appropriate reaching actions to a target object through the learning from scratch without any advance knowledge and any helps of humans . After this learning, the robot could obtain a global representation in the hidden layer by integrating the visual signals, each of which represents local information. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Direct-Vision-Based Reinforcement Learning / real robot / neural network / visual sensor / global representation |
| Paper # | NC2001-154 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2002/3/11(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) | Behavior acquisition for a real robot with a visual sensor by Direct-Vision-Based Reinforcent Learning |
| Sub Title (in English) | |
| Keyword(1) | Direct-Vision-Based Reinforcement Learning |
| Keyword(2) | real robot |
| Keyword(3) | neural network |
| Keyword(4) | visual sensor |
| Keyword(5) | global representation |
| 1st Author's Name | Masaru IIDA |
| 1st Author's Affiliation | Department of Electrical and Electronics Engineering, Faculty of Engineering. Oita University() |
| 2nd Author's Name | Masanori SUGISAKA |
| 2nd Author's Affiliation | Department of Electrical and Electronics Engineering, Faculty of Engineering. Oita University |
| 3rd Author's Name | Katsunari SHIBATA |
| 3rd Author's Affiliation | Department of Electrical and Electronics Engineering, Faculty of Engineering. Oita University |
| Date | 2002/3/11 |
| Paper # | NC2001-154 |
| Volume (vol) | vol.101 |
| Number (no) | 735 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |