Exploration of a Breakthrough Technology for Emergence of Symbol Processing by Neuro-based Reinforcement Learning Considering Time Axis
| Project/Area Number |
23500245
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Oita University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2013: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2012: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2011: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
|
|---|
| Keywords | 知能ロボット / 強化学習 / ニューラルネット / 高次機能 / シンボル処理創発 / 因果トレース / 概念形成 / コミュニケーション学習 / リカレントニューラルネット / ロボット / 動詞表現 / 離散的・抽象的表現 / 自律的役割分担 / 知能創発 / 微分型トレース / 時間軸調整 / 動詞表現獲得 / 時間軸 / コミュニケーション / 自律学習 |
|---|
| Research Abstract |
Efficient learning in a huge amount of spatio-temporal information holds the key to the emergence of higher functions in the real world. In this research, handling of time axis was especially focused on. A novel idea named "Causality traces" is propounded which judge the importance of events "subjectively" and are used for retrospective learning. Its learning performance exceeds that with the conventional method in value learning. Next, based on the idea that "concept" is formed from the difference of necessary motions, it is confirmed that discrete and abstract internal state representations are autonomously formed in a recurrent neural network through reinforcement learning. Furthermore, in autonomous communication learning, it was shown that information about target movement could be transmitted after learning. A novel perspective could be introduced to the handling of the time axis, but for the emergence of symbol processing, learning of dynamics should be further improved.
|
Report
(4 results)
Research Products
(45 results)
