Reinforcement Learning for Systematic FX Trading
This work addresses the problem of profitable and cost-effective trading in currency markets for financial practitioners, though it is incremental as it builds upon earlier methods by incorporating online transfer learning.
The paper tackled systematic foreign exchange trading by developing a reinforcement learning agent that uses online inductive transfer learning to target risk positions, achieving an annualized portfolio information ratio of 0.52 and a compound return of 9.3% net of costs over a 7-year test set.
We explore online inductive transfer learning, with a feature representation transfer from a radial basis function network formed of Gaussian mixture model hidden processing units to a direct, recurrent reinforcement learning agent. This agent is put to work in an experiment, trading the major spot market currency pairs, where we accurately account for transaction and funding costs. These sources of profit and loss, including the price trends that occur in the currency markets, are made available to the agent via a quadratic utility, who learns to target a position directly. We improve upon earlier work by targeting a risk position in an online transfer learning context. Our agent achieves an annualised portfolio information ratio of 0.52 with a compound return of 9.3\%, net of execution and funding cost, over a 7-year test set; this is despite forcing the model to trade at the close of the trading day at 5 pm EST when trading costs are statistically the most expensive.