| Project/Area Number |
19700215
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Tokyo Institute of Technology |
|---|
Principal Investigator |
ITOH Hideaki Tokyo Institute of Technology, 大学院・工学系研究科, 講師 (20345375)
|
|---|
| Project Period (FY) |
2007 – 2010
|
| Project Status |
Completed (Fiscal Year 2010)
|
| Budget Amount *help |
¥2,550,000 (Direct Cost: ¥2,100,000、Indirect Cost: ¥450,000)
Fiscal Year 2010: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2009: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2008: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2007: ¥600,000 (Direct Cost: ¥600,000)
|
|---|
| Keywords | POMDP / 確率的最適制御 / 高次脳機能 / 推論 / 報酬最大化 / 適応制御 / 階層モデル / 階層制御 |
|---|
| Research Abstract |
This study aims at making an agent that is equipped with various "higher brain functions" including the goal-directed reasoning, the selective attention, and the use of working memory. Since it is difficult to make such an agent by hand coding, I try to use the reward maximization principle in order to make an agent that can automatically realize the functions that are suitable for its surrounding environment. In this study, I have been developing a novel method for making such an agent efficiently, based on the theory of partially observable Markov decision processes (POMDPs).
|
