| 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)
|
|---|
| 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.
|
