Object-Oriented Dynamics Learning through Multi-Level Abstraction


  • Guangxiang Zhu Tsinghua university
  • Jianhao Wang Tsinghua University
  • Zhizhou Ren Tsinghua University
  • Zichuan Lin Tsinghua University
  • Chongjie Zhang Tsinghua University




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.




How to Cite

Zhu, G., Wang, J., Ren, Z., Lin, Z., & Zhang, C. (2020). Object-Oriented Dynamics Learning through Multi-Level Abstraction. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 6989-6998. https://doi.org/10.1609/aaai.v34i04.6183



AAAI Technical Track: Machine Learning