2011 Fiscal Year Final Research Report
Research about a conceptual space segmenting agent for emotional communications
| Project/Area Number |
21700242
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Osaka Prefecture University |
|---|
Principal Investigator |
NOTSU Akira 大阪府立大学, 大学院・工学研究科, 助教 (40405345)
|
|---|
| Project Period (FY) |
2009 – 2011
|
| Keywords | 感性情報処理 |
|---|
| Research Abstract |
In this research, learning agents segment its learning space gradually during their trial-and-error processes. We proposed, experienced and discuss several methods about its automation. Additionally, we proposed chain form reinforcement learning for small memory agent. PSO for learning, improvement of complex reinforcement learning, effect of PCA for learning, and multi-agent simulator for CO2 emission are done.
|
