# Learning sparse relational transition models

arXiv: https://arxiv.org/abs/1810.11177 · HTML: https://mlsanity.com/paper/1810.11177/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2018.

## Built on by (most cited first, 11 of 11)

- [Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models](https://mlsanity.com/paper/2401.03360/) (2023)
- [Learning Symbolic Operators for Task and Motion Planning](https://mlsanity.com/paper/2103.00589/) (2021)
- [Grammar Prompting for Domain-Specific Language Generation with Large Language Models](https://mlsanity.com/paper/2305.19234/) (2023)
- [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021)
- [Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning](https://mlsanity.com/paper/2107.12544/) (2021)
- [LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation](https://mlsanity.com/paper/2210.12631/) (2022)
- [Active Learning of Abstract Plan Feasibility](https://mlsanity.com/paper/2107.00683/) (2021)
- [Learning Neuro-symbolic Programs for Language Guided Robot Manipulation](https://mlsanity.com/paper/2211.06652/) (2022)
- [PDSketch: Integrated Planning Domain Programming and Learning](https://mlsanity.com/paper/2303.05501/) (2023)
- [PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent](https://mlsanity.com/paper/2202.00531/) (2022)
- [Macro-Operator Generation and Predicate Selection for TAMP Operator Learning](https://mlsanity.com/paper/2608.23629/) (2026)

## Abstract (arXiv)

We present a representation for describing transition models in complex uncertain domains using relational rules. For any action, a rule selects a set of relevant objects and computes a distribution over properties of just those objects in the resulting state given their properties in the previous state. An iterative greedy algorithm is used to construct a set of deictic references that determine which objects are relevant in any given state. Feed-forward neural networks are used to learn the transition distribution on the relevant objects' properties. This strategy is demonstrated to be both more versatile and more sample efficient than learning a monolithic transition model in a simulated domain in which a robot pushes stacks of objects on a cluttered table.