# S-REINFORCE: A Neuro-Symbolic Policy Gradient Approach for Interpretable Reinforcement Learning

arXiv: https://arxiv.org/abs/2305.07367 · HTML: https://mlsanity.com/paper/2305.07367/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 12 May 2023.

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

- [Scaling Laws for Reward Model Overoptimization](https://mlsanity.com/paper/2210.10760/) (2022)
- [AI Feynman: a Physics-Inspired Method for Symbolic Regression](https://mlsanity.com/paper/1905.11481/) (2019)
- [A Brief Survey of Deep Reinforcement Learning](https://mlsanity.com/paper/1708.05866/) (2017)
- [Benchmarking Deep Reinforcement Learning for Continuous Control](https://mlsanity.com/paper/1604.06778/) (2016)
- [Neural Symbolic Regression that Scales](https://mlsanity.com/paper/2106.06427/) (2021)
- [Deep Reinforcement Learning for De-Novo Drug Design](https://mlsanity.com/paper/1711.10907/) (2017)
- [Interpretable Policies for Reinforcement Learning by Genetic Programming](https://mlsanity.com/paper/1712.04170/) (2017)
- [Symbolic Regression Methods for Reinforcement Learning](https://mlsanity.com/paper/1903.09688/) (2019)
- [Mean Actor Critic](https://mlsanity.com/paper/1709.00503/) (2017)

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

- [Neuro-Symbolic AI: Explainability, Challenges, and Future Trends](https://mlsanity.com/paper/2411.04383/) (2024)
- [Data-Efficient Learning with Neural Programs](https://mlsanity.com/paper/2406.06246/) (2024)
- [Bridging the Gap: Representation Spaces in Neuro-Symbolic AI](https://mlsanity.com/paper/2411.04393/) (2024)

## Abstract (arXiv)

This paper presents a novel RL algorithm, S-REINFORCE, which is designed to generate interpretable policies for dynamic decision-making tasks. The proposed algorithm leverages two types of function approximators, namely Neural Network (NN) and Symbolic Regressor (SR), to produce numerical and symbolic policies, respectively. The NN component learns to generate a numerical probability distribution over the possible actions using a policy gradient, while the SR component captures the functional form that relates the associated states with the action probabilities. The SR-generated policy expressions are then utilized through importance sampling to improve the rewards received during the learning process. We have tested the proposed S-REINFORCE algorithm on various dynamic decision-making problems with low and high dimensional action spaces, and the results demonstrate its effectiveness and impact in achieving interpretable solutions. By leveraging the strengths of both NN and SR, S-REINFORCE produces policies that are not only well-performing but also easy to interpret, making it an ideal choice for real-world applications where transparency and causality are crucial.