An intelligent algorithmic trading based on a risk-return reinforcement learning algorithm
This work addresses portfolio management for algorithmic trading, offering an incremental improvement through a hybrid reinforcement learning approach.
The paper tackles portfolio optimization by developing a deep reinforcement learning algorithm that maximizes a risk-return objective function, incorporating expectation and Value at Risk (VaR). It demonstrates superiority over benchmark strategies in backtesting on two representative portfolios.
This scientific paper propose a novel portfolio optimization model using an improved deep reinforcement learning algorithm. The objective function of the optimization model is the weighted sum of the expectation and value at risk(VaR) of portfolio cumulative return. The proposed algorithm is based on actor-critic architecture, in which the main task of critical network is to learn the distribution of portfolio cumulative return using quantile regression, and actor network outputs the optimal portfolio weight by maximizing the objective function mentioned above. Meanwhile, we exploit a linear transformation function to realize asset short selling. Finally, A multi-process method is used, called Ape-x, to accelerate the speed of deep reinforcement learning training. To validate our proposed approach, we conduct backtesting for two representative portfolios and observe that the proposed model in this work is superior to the benchmark strategies.