A Study on Reinforcement Learning for Analyzing Temporal Data in Finance
| Project/Area Number |
23700182
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Chubu University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2011 – 2012
|
| Project Status |
Completed (Fiscal Year 2012)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2012: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2011: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 機械学習 / 強化学習 / 複利型強化学習 / 人工知能 |
|---|
| Research Abstract |
We developed a new reinforcement learning framework, calledcompound reinforcement learning to bond selection, bond trading, stock trading, n-armedbandit, and blackjack and confirmed that compound reinforcement learning works wellespecially in finance and gambling. We also developed a method to optimize bet fractionparameter in compound reinforcement learning using online gradient method.
|
Report
(3 results)
Research Products
(32 results)
