Reinforcement Learning for Environment with Dynamic Reward using Prior Knowledge
| Project/Area Number |
24760308
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
System engineering
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2012-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 強化学習 / 機械学習 |
|---|
| Outline of Final Research Achievements |
The purpose of this study is to develop efficient reinforcement learning method using prior knowledge for dynamic environment. Because conventional reinforcement learning method assumes that the environment is static, it is hard to be learned.
This study focus on prior knowledge to overcome this difficulty and proposes earning method for environment which has periodicity according time, direction and whose transition probabilities varies according time.
|
Report
(5 results)
Research Products
(17 results)
