Comprehensive Accomplishment of Multiple Language-Related Tasks of Developmental Scales Based on the Theory of Partially Observed Markov Decision Processes
| Project/Area Number |
24500277
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Saga University |
|---|
Principal Investigator |
Itoh Hideaki 佐賀大学, 工学(系)研究科(研究院), 講師 (20345375)
|
|---|
| Project Period (FY) |
2012-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2013: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2012: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | POMDP / 確率的最適制御 / 自然言語処理 / 発達尺度 / 多機能エージェント / 確率モデル / 適応制御 / 階層制御 |
|---|
| Outline of Final Research Achievements |
The aim of this study was to develop an agent that can perform multiple language-related tasks of developmental scales. We have developed a robot that performs multiple tasks including “The subject should answer the number of circles in a given picture (which is a task that can be performed by 3-year-9-month-old children).” Furthermore, we implemented the information processing function necessary for the accomplishment of each task by a combination of functional element modules, and let the agent itself optimize how to combine those modules for a given task. This enabled an efficient development of the agent that can perform multiple tasks.
|
Report
(5 results)
Research Products
(27 results)
