| Project/Area Number |
15300064
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Oita University |
|---|
Principal Investigator |
SHIBATA Katsunari Oita University, Faculty of Engineering, Associate Professor, 工学部, 助教授 (10260522)
|
|---|
| Project Period (FY) |
2003 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥6,500,000 (Direct Cost: ¥6,500,000)
Fiscal Year 2006: ¥1,300,000 (Direct Cost: ¥1,300,000)
Fiscal Year 2005: ¥1,600,000 (Direct Cost: ¥1,600,000)
Fiscal Year 2004: ¥2,100,000 (Direct Cost: ¥2,100,000)
Fiscal Year 2003: ¥1,500,000 (Direct Cost: ¥1,500,000)
|
|---|
| Keywords | Reinforcement Learning / Recurrent Neural Network / Symbol / Robot / Spatial Abstraction / Intelligent Exploration / Temporal Abstraction / Emergence of Intelligence / 乗算ニューロン / 抽象化 / 予測 / 文脈 / 決定論的探索 / 一様探索 / ゲートニューロン / 報酬期待ニューロン / 実用的リカレント学習(PRL) / ニューラルネット / 知能形成 / コミュニケーション / シンボルグラウンディング問題 / カラー情報処理 / 成長型ニューラルネット / 隠れニューロン |
|---|
| Research Abstract |
This research was aimed to show that by the learning using the training signals that are derived by reinforcement learning, various functions emerge according to the necessity in a neural network to which sensor signals are directly entered and whose outputs are motor commands. The main fruits are as follows.
1. It is said that neural networks are not good at symbol processing. However, it was shown that the output representation of a neural network became binary only by reinforcement learning.
2. It was shown that a real robot could learn box-pushing behavior using neural network without giving any informatio a about image processing, image recognition, or the given task.
3. It was shown that a real robot could learn to reach an object in some degree even in a quasi-real world where various objects and colorful leaflets exist.
4. It was shown that a recurrent neural network trained by reinforcement learning could learn some tasks that are thought to be relevant to the spatial or temporal abstraction.
|
