mlsanityData to 7 Oct 2026

Self-supervised Visual Reinforcement Learning with Object-centric Representations

arXiv 2011.14381 ↗First posted 29 Nov 2020cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multi-object environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of the whole scene. We propose to use object-centric representations as a modular and structured observation space, which is learned with a compositional generative world model. We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills. These skills can be further combined to address compositional tasks like the manipulation of several different objects.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 6; 2023: 8; 2024: 14; 2025: 6; 2026: 6.

43 papers.

Sort:

By area:

  1. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  2. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  3. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  4. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  5. 2024Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imaginationcited by 45
  6. 2024Temporally Consistent Object-Centric Learning by Contrasting Slotscited by 30
  7. 2024Entity-Centric Reinforcement Learning for Object Manipulation from Pixelscited by 27
  8. 2022Policy Architectures for Compositional Generalization in Controlcited by 23
  9. 2021Towards Deeper Deep Reinforcement Learning with Spectral Normalizationcited by 19
  10. 2022Compositional Multi-Object Reinforcement Learning with Linear Relation Networkscited by 19
  11. 2024Zero-Shot Object-Centric Representation Learningcited by 19
  12. 2021Self-supervised Reinforcement Learning with Independently Controllable Subgoalscited by 16
31 more
  1. 2025Object-Centric World Model for Language-Guided Manipulationcited by 16
  2. 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learningcited by 15
  3. 2024BlendRL: A Framework for Merging Symbolic and Neural Policy Learningcited by 14
  4. 2022Learning to Generalize with Object-centric Agents in the Open World Survival Game Craftercited by 13
  5. 2025CTRL-O: Language-Controllable Object-Centric Visual Representation Learningcited by 12
  6. 2022Unsupervised Multi-object Segmentation Using Attention and Soft-argmaxcited by 11
  7. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  8. 2021Object-Centric Representation Learning with Generative Spatial-Temporal Factorizationcited by 10
  9. 2024Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learningcited by 10
  10. 2024SkiLD: Unsupervised Skill Discovery Guided by Factor Interactionscited by 9
  11. 2025SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Modelscited by 9
  12. 2024Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discoverycited by 8
  13. 2024EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generationcited by 8
  14. 2022Object-Category Aware Reinforcement Learningcited by 6
  15. 2025Object-Centric Pretraining via Target Encoder Bootstrappingcited by 6
  16. 2026Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusioncited by 6
  17. 2024Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biasescited by 5
  18. 2026OCRA: Object-Centric Learning with 3D and Tactile Priors for Human-to-Robot Action Transfercited by 5
  19. 2023Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learningcited by 4
  20. 2023Relational Object-Centric Actor-Criticcited by 4
  21. 2023Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Reviewcited by 3
  22. 2024OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematicscited by 3
  23. 2024Learning Causal Dynamics Models in Object-Oriented Environmentscited by 3
  24. 2025Object-Centric World Models for Causality-Aware Reinforcement Learningcited by 3
  25. 2024Object-centric proto-symbolic behavioural reasoning from pixelscited by 2
  26. 2023Discovering Object-Centric Generalized Value Functions From Pixelscited by 1
  27. 2024Unsupervised Salient Patch Selection for Data-Efficient Reinforcement Learningcited by 0
  28. 2026QASA: Quality-Guided K-Adaptive Slot Attention for Unsupervised Object-Centric Learningcited by 0
  29. 2026GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learningcited by 0
  30. 2026Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planningcited by 0
  31. 2026Semantic Slots for Video Object-Centric Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning
  2. 2024Learning to Compose: Improving Object Centric Learning by Injecting Compositionality
  3. 2024Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
  4. 2025Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning
  5. 2024Learning from 10 Demos: Generalisable and Sample-Efficient Policy Learning with Oriented Affordance Frames
  6. 2024Vision-Language Models Provide Promptable Representations for Reinforcement Learning
  7. 2025Iterative Compositional Data Generation for Robot Control
  8. 2019Supervise Thyself: Examining Self-Supervised Representations in Interactive Environments