Fourth year PhD student in the Economics and Computation Group at the University of Liverpool following a Master’s in Physics. The focus of my research is on the applications of reinforcement learning for optimising decision problems in complex real-world domains including automated trading (market-making, optimal execution, statistical arbitrage, order routing) and epidemiology which are heavily influenced by the minimisation of risk.
MPhys in Physics, 2016
University of Liverpool
Market making is a fundamental trading problem in which an agent provides liquidity by continually offering to buy and sell a security. The problem is challenging due to inventory risk, the risk of accumulating an unfavourable position and ultimately losing money. In this paper, we develop a high-fidelity simulation of limit order book markets, and use it to design a market making agent using temporal-difference reinforcement learning. We use a linear combination of tile codings as a value function approximator, and design a custom reward function that controls inventory risk. We demonstrate the effectiveness of our approach by showing that our agent outperforms both simple benchmark strategies and a recent online learning approach from the literature.