# Learning Portable Representations for High-Level Planning

arXiv: https://arxiv.org/abs/1905.12006 · HTML: https://mlsanity.com/paper/1905.12006/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2019.

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

- [Learning Neuro-Symbolic Skills for Bilevel Planning](https://mlsanity.com/paper/2206.10680/) (2022)
- [VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning](https://mlsanity.com/paper/2410.23156/) (2024)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Discovering User-Interpretable Capabilities of Black-Box Planning Agents](https://mlsanity.com/paper/2107.13668/) (2021)
- [MinePlanner: A Benchmark for Long-Horizon Planning in Large Minecraft Worlds](https://mlsanity.com/paper/2312.12891/) (2023)
- [Learning Abstract World Model for Value-preserving Planning with Options](https://mlsanity.com/paper/2406.15850/) (2024)
- [Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning](https://mlsanity.com/paper/2503.21406/) (2025)
- [Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning](https://mlsanity.com/paper/2207.05018/) (2022)
- [Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers](https://mlsanity.com/paper/2309.00889/) (2023)
- [Creativity of AI: Hierarchical Planning Model Learning for Facilitating Deep Reinforcement Learning](https://mlsanity.com/paper/2112.09836/) (2021)
- [Autonomous Assessment of Generalizability of AI Agent Capabilities](https://mlsanity.com/paper/2512.16733/) (2025)

## Abstract (arXiv)

We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent that, when grounded with problem-specific information, are provably sufficient for planning. We demonstrate transfer in two different domains, where an agent learns a portable, task-independent symbolic vocabulary, as well as rules expressed in that vocabulary, and then learns to instantiate those rules on a per-task basis. This reduces the number of samples required to learn a representation of a new task.