Reinforced Deep Markov Models With Applications in Automatic Trading
This work addresses the challenge of developing robust automatic trading systems for financial markets, though it appears incremental as it builds on existing deep generative and reinforcement learning methods.
The authors tackled the problem of automatic trading in complex market environments by proposing a Reinforced Deep Markov Model (RDMM) that filters noisy data for reinforcement learning planning, resulting in data-efficient policies that achieved financial gains compared to benchmarks like Q-Learning and DynaQ variants, with improvements demonstrated on real limit order book data from companies such as Facebook and Microsoft.
Inspired by the developments in deep generative models, we propose a model-based RL approach, coined Reinforced Deep Markov Model (RDMM), designed to integrate desirable properties of a reinforcement learning algorithm acting as an automatic trading system. The network architecture allows for the possibility that market dynamics are partially visible and are potentially modified by the agent's actions. The RDMM filters incomplete and noisy data, to create better-behaved input data for RL planning. The policy search optimisation also properly accounts for state uncertainty. Due to the complexity of the RKDF model architecture, we performed ablation studies to understand the contributions of individual components of the approach better. To test the financial performance of the RDMM we implement policies using variants of Q-Learning, DynaQ-ARIMA and DynaQ-LSTM algorithms. The experiments show that the RDMM is data-efficient and provides financial gains compared to the benchmarks in the optimal execution problem. The performance improvement becomes more pronounced when price dynamics are more complex, and this has been demonstrated using real data sets from the limit order book of Facebook, Intel, Vodafone and Microsoft.