# Learning First-Order Symbolic Planning Representations That Are Grounded

arXiv: https://arxiv.org/abs/2204.11902 · HTML: https://mlsanity.com/paper/2204.11902/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 81 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 12 of 12)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [Multi-shot ASP solving with clingo](https://mlsanity.com/paper/1705.09811/) (2017)
- [Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary](https://mlsanity.com/paper/1705.00154/) (2017)
- [PDDLGym: Gym Environments from PDDL Problems](https://mlsanity.com/paper/2002.06432/) (2020)
- [Learning First-Order Symbolic Representations for Planning from the Structure of the State Space](https://mlsanity.com/paper/1909.05546/) (2019)
- [Learning Features and Abstract Actions for Computing Generalized Plans](https://mlsanity.com/paper/1811.07231/) (2018)
- [Unsupervised Grounding of Plannable First-Order Logic Representation from Images](https://mlsanity.com/paper/1902.08093/) (2019)
- [Understanding the Power and Limitations of Teaching with Imperfect Knowledge](https://mlsanity.com/paper/2003.09712/) (2020)
- [Learning First-Order Representations for Planning from Black-Box States: New Results](https://mlsanity.com/paper/2105.10830/) (2021)
- [Efficient, Safe, and Probably Approximately Complete Learning of Action Models](https://mlsanity.com/paper/1705.08961/) (2017)

## Built on by (most cited first, 2 of 2)

- [Planning for Learning Object Properties](https://mlsanity.com/paper/2301.06054/) (2023)
- [Language-Based Causal Representation Learning](https://mlsanity.com/paper/2207.05259/) (2022)

## Abstract (arXiv)

Two main approaches have been developed for learning first-order planning (action) models from unstructured data: combinatorial approaches that yield crisp action schemas from the structure of the state space, and deep learning approaches that produce action schemas from states represented by images. A benefit of the former approach is that the learned action schemas are similar to those that can be written by hand; a benefit of the latter is that the learned representations (predicates) are grounded on the images, and as a result, new instances can be given in terms of images. In this work, we develop a new formulation for learning crisp first-order planning models that are grounded on parsed images, a step to combine the benefits of the two approaches. Parsed images are assumed to be given in a simple O2D language (objects in 2D) that involves a small number of unary and binary predicates like "left", "above", "shape", etc. After learning, new planning instances can be given in terms of pairs of parsed images, one for the initial situation and the other for the goal. Learning and planning experiments are reported for several domains including Blocks, Sokoban, IPC Grid, and Hanoi.