# Neuro-symbolic Meta Reinforcement Learning for Trading

arXiv: https://arxiv.org/abs/2302.08996 · HTML: https://mlsanity.com/paper/2302.08996/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 15 Jan 2023.

## Builds on (most cited first, 9 of 9)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Deep Reinforcement Learning for Trading](https://mlsanity.com/paper/1911.10107/) (2019)
- [Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture](https://mlsanity.com/paper/2112.08534/) (2021)
- [Dynamical Models of Stock Prices Based on Technical Trading Rules Part II: Analysis of the Models](https://mlsanity.com/paper/1401.1891/) (2014)
- [Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!](https://mlsanity.com/paper/2110.10233/) (2021)

## Built on by (most cited first, 3 of 3)

- [Neuro-Symbolic AI in 2024: A Systematic Review](https://mlsanity.com/paper/2501.05435/) (2025)
- [Conservative Predictions on Noisy Financial Data](https://mlsanity.com/paper/2310.11815/) (2023)
- [Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability](https://mlsanity.com/paper/2607.18368/) (2026)

## Abstract (arXiv)

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.