Deep Reinforcement Learning in Cryptocurrency Market Making

TL;DR

This paper introduces a deep reinforcement learning framework for cryptocurrency market making, demonstrating its effectiveness in managing stochastic inventory control through policy gradient algorithms and neural networks.

Contribution

It presents a novel DRL-based approach for cryptocurrency market making, comparing reward functions and validating performance with real market data.

Findings

Deep RL can effectively address stochastic inventory control in crypto markets.

Policy gradient algorithms outperform traditional methods in this setting.

Reward function choice significantly impacts trading performance.

Abstract

This paper sets forth a framework for deep reinforcement learning as applied to market making (DRLMM) for cryptocurrencies. Two advanced policy gradient-based algorithms were selected as agents to interact with an environment that represents the observation space through limit order book data, and order flow arrival statistics. Within the experiment, a forward-feed neural network is used as the function approximator and two reward functions are compared. The performance of each combination of agent and reward function is evaluated by daily and average trade returns. Using this DRLMM framework, this paper demonstrates the effectiveness of deep reinforcement learning in solving stochastic inventory control challenges market makers face.