Profitable stock trading strategy is vital to investment companies. It is applied to optimize allocationof capital and thus maximize performance, such as expected return. Return maximization is basedon estimates of stocks’ potential return and risk. However, it is challenging for analysts to take allrelavant factors into consideration in complex stock marke

Stock trading strategy plays a crucial role in investment companies. However, it ischallenging to obtain optimal strategy in the complex and dynamic stock market.We explore the potential of deep reinforcement learning to optimize stock tradingstrategy and thus maximize investment return. 30 stocks are selected as our tradingstocks and their daily prices are used as the training and trading market environment.We train a deep reinforcement learning agent and obtain an adaptive trading strategy.The agent’s performance is evaluated and compared with Dow Jones IndustrialAverage and the traditional min-variance portfolio allocation strategy. The proposeddeep reinforcement learning approach is shown to outperform the two baselines interms of both the Sharpe ratio and cumulative returns.