Consistent time travel for realistic interactions with historical data: reinforcement learning for market making

TL;DR

This paper introduces a novel approach called consistent data time travel for offline reinforcement learning, enabling more realistic interactions with historical data, demonstrated in market making where it improves agent gains significantly.

Contribution

The paper proposes a new method for offline RL called consistent data time travel, addressing simulation and data inference challenges in multi-agent systems like financial markets.

Findings

Data time travel improves RL agent gains in market making.

The approach reduces the overestimation of RL difficulty in complex tasks.

It alleviates the need for imperfect models in offline RL.

Abstract

Reinforcement learning works best when the impact of the agent's actions on its environment can be perfectly simulated or fully appraised from available data. Some systems are however both hard to simulate and very sensitive to small perturbations. An additional difficulty arises when a RL agent is trained offline to be part of a multi-agent system using only anonymous data, which makes it impossible to infer the state of each agent, thus to use data directly. Typical examples are competitive systems without agent-resolved data such as financial markets. We introduce consistent data time travel for offline RL as a remedy for these problems: instead of using historical data in a sequential way, we argue that one needs to perform time travel in historical data, i.e., to adjust the time index so that both the past state and the influence of the RL agent's action on the system coincide with real data. This both alleviates the need to resort to imperfect models and consistently accounts for both the immediate and long-term reactions of the system when using anonymous historical data. We apply this idea to market making in limit order books, a notoriously difficult task for RL; it turns out that the gain of the agent is significantly higher with data time travel than with naive sequential data, which suggests that the difficulty of this task for RL may have been overestimated.