A simple learning agent interacting with an agent-based market model
This work addresses the impact of AI-driven trading strategies on financial market simulations, but it is incremental as it builds on existing agent-based models and reinforcement learning methods.
The study examined how a reinforcement learning optimal execution trading agent affects an agent-based financial market model, finding that smaller state space agents converged faster and learned intuitive trading strategies, while the market's Hurst exponent decreased and trade-sign auto-correlations reduced with higher trading volumes.
We consider the learning dynamics of a single reinforcement learning optimal execution trading agent when it interacts with an event driven agent-based financial market model. Trading takes place asynchronously through a matching engine in event time. The optimal execution agent is considered at different levels of initial order-sizes and differently sized state spaces. The resulting impact on the agent-based model and market are considered using a calibration approach that explores changes in the empirical stylised facts and price impact curves. Convergence, volume trajectory and action trace plots are used to visualise the learning dynamics. Here the smaller state space agents had the number of states they visited converge much faster than the larger state space agents, and they were able to start learning to trade intuitively using the spread and volume states. We find that the moments of the model are robust to the impact of the learning agents except for the Hurst exponent, which was lowered by the introduction of strategic order-splitting. The introduction of the learning agent preserves the shape of the price impact curves but can reduce the trade-sign auto-correlations when their trading volumes increase.