Adversarial Deep Reinforcement Learning in Portfolio Management
This work addresses portfolio optimization for financial traders, but it is incremental as it applies existing methods to a new domain with a minor modification.
The paper tackled portfolio management by applying three continuous reinforcement learning algorithms (DDPG, PPO, PG) to the China Stock market, finding that PG performed best and that an adversarial training method improved training efficiency and increased average daily return and Sharpe ratio in backtests.
In this paper, we implement three state-of-art continuous reinforcement learning algorithms, Deep Deterministic Policy Gradient (DDPG), Proximal Policy Optimization (PPO) and Policy Gradient (PG)in portfolio management. All of them are widely-used in game playing and robot control. What's more, PPO has appealing theoretical propeties which is hopefully potential in portfolio management. We present the performances of them under different settings, including different learning rates, objective functions, feature combinations, in order to provide insights for parameters tuning, features selection and data preparation. We also conduct intensive experiments in China Stock market and show that PG is more desirable in financial market than DDPG and PPO, although both of them are more advanced. What's more, we propose a so called Adversarial Training method and show that it can greatly improve the training efficiency and significantly promote average daily return and sharpe ratio in back test. Based on this new modification, our experiments results show that our agent based on Policy Gradient can outperform UCRP.