# Neural NID Rules

arXiv: https://arxiv.org/abs/2202.06036 · HTML: https://mlsanity.com/paper/2202.06036/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 12 Feb 2022.

## Builds on (most cited first, 11 of 11)

- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Discovering Symbolic Models from Deep Learning with Inductive Biases](https://mlsanity.com/paper/2006.11287/) (2020)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [Neural Expectation Maximization](https://mlsanity.com/paper/1708.03498/) (2017)
- [Entity Abstraction in Visual Model-Based Reinforcement Learning](https://mlsanity.com/paper/1910.12827/) (2019)
- [Unsupervised Learning of Object Keypoints for Perception and Control](https://mlsanity.com/paper/1906.11883/) (2019)
- [Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions](https://mlsanity.com/paper/1802.10353/) (2018)
- [Neural Logic Reinforcement Learning](https://mlsanity.com/paper/1904.10729/) (2019)
- [PDDLGym: Gym Environments from PDDL Problems](https://mlsanity.com/paper/2002.06432/) (2020)

## Abstract (arXiv)

Abstract object properties and their relations are deeply rooted in human common sense, allowing people to predict the dynamics of the world even in situations that are novel but governed by familiar laws of physics. Standard machine learning models in model-based reinforcement learning are inadequate to generalize in this way. Inspired by the classic framework of noisy indeterministic deictic (NID) rules, we introduce here Neural NID, a method that learns abstract object properties and relations between objects with a suitably regularized graph neural network. We validate the greater generalization capability of Neural NID on simple benchmarks specifically designed to assess the transition dynamics learned by the model.