Neuro-symbolic Meta Reinforcement Learning for Trading

2023/01/15 by S I Harini, Gautam Shroff, Harini, S I +7
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #Data Stream Mining Techniques #FOS: Computer and information sciences #Logic in Computer Science (cs.LO) #Machine Learning (cs.LG) #Stock Market Forecasting Methods

paper · pdf · doi:10.48550/arxiv.2302.08996

openalex publication_date 2023/01/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• When AI Trading Agents Compete: Adverse Selection of Meta-Orders by Reinforcement Learning-Based Market Making
• Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review
• A new method for generating trading signals in financial markets using a combination of deep learning and reinforcement learning.
• Logic-Q: Improving Deep Reinforcement Learning-based Quantitative Trading via Program Sketch-based Tuning
• Model-based Reinforcement Learning for Predictions and Control for Limit Order Books