Portfolio Management based on Deep Reinforcement Learning with Adaptive Sampling

Quantitative trading finds stable and profitable trading strategies by observing historical data through statistics or mathematics methods. However, existing studies are still insufficient for the generalization of trading strategies. Therefore, this study takes the constituents of the Dow Jones Industrial Average as the target and applies the problem of optimizing the portfolio. The goal is to construct a portfolio of five assets from the constituent stocks, and this portfolio could achieve excellent performance through our trading strategy. Also, this study proposes a sampling strategy to determine which data is worth learning by observing the learning condition in order to save computational time. From the result of the experiment, we could observe that the model with our sampling strategy performed 6-7 % better than our baselines in terms of Sharpe ratio.