# Object-Oriented Dynamics Learning through Multi-Level Abstraction

arXiv: https://arxiv.org/abs/1904.07482 · HTML: https://mlsanity.com/paper/1904.07482/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2019.

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

- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [Learning Causal Dynamics Models in Object-Oriented Environments](https://mlsanity.com/paper/2405.12615/) (2024)

## Abstract (arXiv)

Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-supervised learning framework, called Multi-level Abstraction Object-oriented Predictor (MAOP), which employs a three-level learning architecture that enables efficient object-based dynamics learning from raw visual observations. We also design a spatial-temporal relational reasoning mechanism for MAOP to support instance-level dynamics learning and handle partial observability. Our results show that MAOP significantly outperforms previous methods in terms of sample efficiency and generalization over novel environments for learning environment models. We also demonstrate that learned dynamics models enable efficient planning in unseen environments, comparable to true environment models. In addition, MAOP learns semantically and visually interpretable disentangled representations.