| Budget Amount *help |
¥17,160,000 (Direct Cost: ¥13,200,000、Indirect Cost: ¥3,960,000)
Fiscal Year 2019: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2018: ¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2017: ¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2016: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2015: ¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
|
|---|
| Outline of Final Research Achievements |
We proposed ADPRL (Approximate Dynamic Programming & Reinforcement Learning) as a distinct approach to numerical computation that enables quantitative analysis that is practically useful for financial problems and management decision-making problems where various uncertainties exist that cannot be analyzed analytically.
We thoroughly studied three factors: modeling, simulation, and numerical optimization, and have constructed an integrated framework.
Next, based on ADPRL, we analyzed various applications under high -dimensionality, ambiguity and/or model uncertainty for actual management to analyze both risk and returns and to make the optimal decisions.
|
