# Toward Compositional Generalization in Object-Oriented World Modeling

arXiv: https://arxiv.org/abs/2204.13661 · HTML: https://mlsanity.com/paper/2204.13661/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 28 Apr 2022.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 23 of 23)

- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [MONet: Unsupervised Scene Decomposition and Representation](https://mlsanity.com/paper/1901.11390/) (2019)
- [Towards a Definition of Disentangled Representations](https://mlsanity.com/paper/1812.02230/) (2018)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [Conditional Object-Centric Learning from Video](https://mlsanity.com/paper/2111.12594/) (2021)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Contrastive Learning of Structured World Models](https://mlsanity.com/paper/1911.12247/) (2019)
- [Universal Invariant and Equivariant Graph Neural Networks](https://mlsanity.com/paper/1905.04943/) (2019)
- [A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms](https://mlsanity.com/paper/1907.03146/) (2019)
- [MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning](https://mlsanity.com/paper/2006.16908/) (2020)
- [Entity Abstraction in Visual Model-Based Reinforcement Learning](https://mlsanity.com/paper/1910.12827/) (2019)
- [Compositionality and Generalization in Emergent Languages](https://mlsanity.com/paper/2004.09124/) (2020)
- [Measuring Compositionality in Representation Learning](https://mlsanity.com/paper/1902.07181/) (2019)
- [Neural Production Systems: Learning Rule-Governed Visual Dynamics](https://mlsanity.com/paper/2103.01937/) (2021)
- [Improving Generative Imagination in Object-Centric World Models](https://mlsanity.com/paper/2010.02054/) (2020)
- [COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration](https://mlsanity.com/paper/1905.09275/) (2019)
- [Structured Object-Aware Physics Prediction for Video Modeling and Planning](https://mlsanity.com/paper/1910.02425/) (2019)
- [Symmetry-Based Disentangled Representation Learning requires Interaction with Environments](https://mlsanity.com/paper/1904.00243/) (2019)
- [Unsupervised Object-Based Transition Models for 3D Partially Observable Environments](https://mlsanity.com/paper/2103.04693/) (2021)
- [Binding Actions to Objects in World Models](https://mlsanity.com/paper/2204.13022/) (2022)
- [The Impact of Negative Sampling on Contrastive Structured World Models](https://mlsanity.com/paper/2107.11676/) (2021)

## Built on by (most cited first, 22 of 22)

- [Provable Compositional Generalization for Object-Centric Learning](https://mlsanity.com/paper/2310.05327/) (2023)
- [Entity-Centric Reinforcement Learning for Object Manipulation from Pixels](https://mlsanity.com/paper/2404.01220/) (2024)
- [Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning](https://mlsanity.com/paper/2307.09205/) (2023)
- [Neurosymbolic Grounding for Compositional World Models](https://mlsanity.com/paper/2310.12690/) (2023)
- [Dyn-O: Building Structured World Models with Object-Centric Representations](https://mlsanity.com/paper/2507.03298/) (2025)
- [A Survey on Compositional Generalization in Applications](https://mlsanity.com/paper/2302.01067/) (2023)
- [Language-Guided World Models: A Model-Based Approach to AI Control](https://mlsanity.com/paper/2402.01695/) (2024)
- [Entity-based Reinforcement Learning for Autonomous Cyber Defence](https://mlsanity.com/paper/2410.17647/) (2024)
- [Learning Interactive World Model for Object-Centric Reinforcement Learning](https://mlsanity.com/paper/2511.02225/) (2025)
- [EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation](https://mlsanity.com/paper/2412.18907/) (2024)
- [Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion](https://mlsanity.com/paper/2602.02722/) (2026)
- [Integrating Symmetry into Differentiable Planning with Steerable Convolutions](https://mlsanity.com/paper/2206.03674/) (2022)
- [E(2)-Equivariant Graph Planning for Navigation](https://mlsanity.com/paper/2309.13043/) (2023)
- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [Equivariant Action Sampling for Reinforcement Learning and Planning](https://mlsanity.com/paper/2412.12237/) (2024)
- [Towards Understanding Extrapolation: a Causal Lens](https://mlsanity.com/paper/2501.09163/) (2025)
- [Dreamweaver: Learning Compositional World Models from Pixels](https://mlsanity.com/paper/2501.14174/) (2025)
- [From monoliths to modules: Decomposing transducers for efficient world modelling](https://mlsanity.com/paper/2512.02193/) (2025)
- [What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives](https://mlsanity.com/paper/2510.03075/) (2025)
- [Can Euclidean Symmetry be Leveraged in Reinforcement Learning and Planning?](https://mlsanity.com/paper/2307.08226/) (2023)
- [State Combinatorial Generalization In Decision Making With Conditional Diffusion Models](https://mlsanity.com/paper/2501.13241/) (2025)
- [Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis](https://mlsanity.com/paper/2605.07821/) (2026)

## Abstract (arXiv)

Compositional generalization is a critical ability in learning and decision-making. We focus on the setting of reinforcement learning in object-oriented environments to study compositional generalization in world modeling. We (1) formalize the compositional generalization problem with an algebraic approach and (2) study how a world model can achieve that. We introduce a conceptual environment, Object Library, and two instances, and deploy a principled pipeline to measure the generalization ability. Motivated by the formulation, we analyze several methods with exact or no compositional generalization ability using our framework, and design a differentiable approach, Homomorphic Object-oriented World Model (HOWM), that achieves soft but more efficient compositional generalization.