# A Perspective on Objects and Systematic Generalization in Model-Based RL

arXiv: https://arxiv.org/abs/1906.01035 · HTML: https://mlsanity.com/paper/1906.01035/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 14 of 14)

- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning](https://mlsanity.com/paper/2302.04419/) (2023)
- [Capturing the objects of vision with neural networks](https://mlsanity.com/paper/2109.03351/) (2021)
- [GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models](https://mlsanity.com/paper/2310.20025/) (2023)
- [Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models](https://mlsanity.com/paper/2404.13474/) (2024)
- [Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies](https://mlsanity.com/paper/2405.15916/) (2024)
- [Modular Object-Oriented Games: A Task Framework for Reinforcement Learning, Psychology, and Neuroscience](https://mlsanity.com/paper/2102.12616/) (2021)
- [Exploring the Role of the Bottleneck in Slot-Based Models Through Covariance Regularization](https://mlsanity.com/paper/2306.02577/) (2023)
- [Pretrained Encoders are All You Need](https://mlsanity.com/paper/2106.05139/) (2021)
- [The Impact of Negative Sampling on Contrastive Structured World Models](https://mlsanity.com/paper/2107.11676/) (2021)
- [Discovering Object-Centric Generalized Value Functions From Pixels](https://mlsanity.com/paper/2304.13892/) (2023)
- [Cyclophobic Reinforcement Learning](https://mlsanity.com/paper/2308.15911/) (2023)
- [OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning](https://mlsanity.com/paper/2310.18807/) (2023)
- [Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representations](https://mlsanity.com/paper/2503.09867/) (2025)

## Abstract (arXiv)

In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the combinatorial construction of such models. In this work, we argue that dynamically bound features (objects) do not simply emerge in connectionist models of the world. We identify several requirements that need to be fulfilled in overcoming this limitation and highlight corresponding inductive biases.