# Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies

arXiv: https://arxiv.org/abs/2501.03888 · HTML: https://mlsanity.com/paper/2501.03888/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 7 Jan 2025.

## Placed in

- Deep reinforcement learning methods / [Interpretable and logic-guided RL](https://mlsanity.com/deeprl/interpretable-and-logic-guided-rl/)

## Builds on (most cited first, 19 of 19)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [Programmatically Interpretable Reinforcement Learning](https://mlsanity.com/paper/1804.02477/) (2018)
- [Neural Logic Machines](https://mlsanity.com/paper/1904.11694/) (2019)
- [Logical Neural Networks](https://mlsanity.com/paper/2006.13155/) (2020)
- [Relational Deep Reinforcement Learning](https://mlsanity.com/paper/1806.01830/) (2018)
- [Neural Logic Reinforcement Learning](https://mlsanity.com/paper/1904.10729/) (2019)
- [Inductive logic programming at 30](https://mlsanity.com/paper/2102.10556/) (2021)
- [Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction](https://mlsanity.com/paper/2306.01439/) (2023)
- [Neuro-Symbolic Reinforcement Learning with First-Order Logic](https://mlsanity.com/paper/2110.10963/) (2021)
- [Differentiable Inductive Logic Programming for Structured Examples](https://mlsanity.com/paper/2103.01719/) (2021)
- [Automatic Gesture Recognition in Robot-assisted Surgery with Reinforcement Learning and Tree Search](https://mlsanity.com/paper/2002.08718/) (2020)
- [Differentiable Logic Machines](https://mlsanity.com/paper/2102.11529/) (2021)
- [GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis](https://mlsanity.com/paper/2205.13728/) (2022)
- [pix2rule: End-to-end Neuro-symbolic Rule Learning](https://mlsanity.com/paper/2106.07487/) (2021)
- [Neuro-symbolic Rule Learning in Real-world Classification Tasks](https://mlsanity.com/paper/2303.16674/) (2023)

## Built on by (most cited first, 4 of 4)

- [Local-to-Global Logical Explanations for Deep Vision Models](https://mlsanity.com/paper/2601.13404/) (2026)
- [Disentangling Neural Disjunctive Normal Form Models](https://mlsanity.com/paper/2507.10546/) (2025)
- [Visual Perceptual to Conceptual First-Order Rule Learning Networks](https://mlsanity.com/paper/2604.07897/) (2026)
- [GLARE: A Natural Language Interface for Querying Global Explanations](https://mlsanity.com/paper/2606.19735/) (2026)

## Abstract (arXiv)

Although deep reinforcement learning has been shown to be effective, the model's black-box nature presents barriers to direct policy interpretation. To address this problem, we propose a neuro-symbolic approach called neural DNF-MT for end-to-end policy learning. The differentiable nature of the neural DNF-MT model enables the use of deep actor-critic algorithms for training. At the same time, its architecture is designed so that trained models can be directly translated into interpretable policies expressed as standard (bivalent or probabilistic) logic programs. Moreover, additional layers can be included to extract abstract features from complex observations, acting as a form of predicate invention. The logic representations are highly interpretable, and we show how the bivalent representations of deterministic policies can be edited and incorporated back into a neural model, facilitating manual intervention and adaptation of learned policies. We evaluate our approach on a range of tasks requiring learning deterministic or stochastic behaviours from various forms of observations. Our empirical results show that our neural DNF-MT model performs at the level of competing black-box methods whilst providing interpretable policies.