| Project/Area Number |
16K12485
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Yokohama National University |
|---|
Principal Investigator |
HAMAGAMI Tomoki 横浜国立大学, 大学院工学研究院, 教授 (30334204)
|
|---|
| Project Period (FY) |
2016-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2017: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2016: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | 逆強化学習 / 強化学習 / アンサンブル学習 / 不完全知覚 / ブースティング / 機械学習 / 知能情報処理 |
|---|
| Outline of Final Research Achievements |
Ensemble inverse reinforcement learning from semi-experts' behavior is proposed. In many inverse reinforcement learning (IRL) problems, the expert agent which has ideal rewards for achieving the goal is supposed to be existing. However, in real-world problem, the expert is not always observed. Moreover, the estimated reward function includes the bias depending on its inherent behavior if the reward for achieving the goal
task is estimated from one agent. In order to overcome the limitation of IRL, we apply Adaboost, one of ensemble and boosting approach, to IRL and integrate estimated reward functions from semi-expert agents. To confirm the effectiveness of the proposed method in the grid world including incomplete areas, we compared the results of reinforcement learning using estimated reward functions and integrated reward function by simulation. The simulation result shows the proposed method can estimate the reward
adaptively.
|
