Neuro-symbolic Meta Reinforcement Learning for Trading

TL;DR

This paper introduces a neuro-symbolic meta reinforcement learning approach for day trading, combining meta-RL with symbolic pattern discovery to adapt to market changes and improve trading performance.

Contribution

It integrates logical program induction with meta-RL to leverage symbolic patterns, enhancing adaptability and decision-making in financial trading environments.

Findings

Meta-RL outperforms vanilla RL in trading tasks.

Symbolic features improve trading performance.

The approach adapts to concept drift in financial markets.

Abstract

We model short-duration (e.g. day) trading in financial markets as a sequential decision-making problem under uncertainty, with the added complication of continual concept-drift. We, therefore, employ meta reinforcement learning via the RL2 algorithm. It is also known that human traders often rely on frequently occurring symbolic patterns in price series. We employ logical program induction to discover symbolic patterns that occur frequently as well as recently, and explore whether using such features improves the performance of our meta reinforcement learning algorithm. We report experiments on real data indicating that meta-RL is better than vanilla RL and also benefits from learned symbolic features.