mlsanityData to 14 Oct 2026

COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration

arXiv 1905.09275 ↗First posted 22 May 2019cs.LG cs.AIcited by 57

Not on the map. Why?

Abstract (arXiv)

Data efficiency and robustness to task-irrelevant perturbations are long-standing challenges for deep reinforcement learning algorithms. Here we introduce a modular approach to addressing these challenges in a continuous control environment, without using hand-crafted or supervised information. Our Curious Object-Based seaRch Agent (COBRA) uses task-free intrinsically motivated exploration and unsupervised learning to build object-based models of its environment and action space. Subsequently, it can learn a variety of tasks through model-based search in very few steps and excel on structured hold-out tests of policy robustness.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 13; 2023: 12; 2024: 6; 2025: 8; 2026: 3.

57 papers.

Sort:

By area:

  1. 2021Towards Causal Representation Learningcited by 209
  2. 2021BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environmentscited by 165
  3. 2021Physion: Evaluating Physical Prediction from Vision in Humans and Machinescited by 153
  4. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  5. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  6. 2021Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learningcited by 53
  7. 2022Retrieval-Augmented Reinforcement Learningcited by 53
  8. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  9. 2021Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planningcited by 43
  10. 2022Neural Systematic Bindercited by 37
  11. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  12. 2022Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulationcited by 31
38 more
  1. 2022Compositional Scene Representation Learning via Reconstruction: A Surveycited by 27
  2. 2024Entity-Centric Reinforcement Learning for Object Manipulation from Pixelscited by 27
  3. 2021Generative Video Transformer: Can Objects be the Words?cited by 24
  4. 2022Toward Compositional Generalization in Object-Oriented World Modelingcited by 22
  5. 2021Structured World Belief for Reinforcement Learning in POMDPcited by 21
  6. 2021Unsupervised Object-Based Transition Models for 3D Partially Observable Environmentscited by 20
  7. 2022Unsupervised Image Representation Learning with Deep Latent Particlescited by 19
  8. 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learningcited by 15
  9. 2023Neurosymbolic Grounding for Compositional World Modelscited by 14
  10. 2022Learning to Generalize with Object-centric Agents in the Open World Survival Game Craftercited by 13
  11. 2023Combining Behaviors with the Successor Features Keyboardcited by 12
  12. 2021Temporally Abstract Partial Modelscited by 11
  13. 2023Object-Centric Learning with Slot Mixture Modulecited by 11
  14. 2025Are We Done with Object-Centric Learning?cited by 11
  15. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  16. 2021Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reductioncited by 9
  17. 2024Language Agents Meet Causality -- Bridging LLMs and Causal World Modelscited by 9
  18. 2021GATSBI: Generative Agent-centric Spatio-temporal Object Interactioncited by 8
  19. 2023DAVA: Disentangling Adversarial Variational Autoencodercited by 8
  20. 2022Object-based active inferencecited by 7
  21. 2026Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusioncited by 7
  22. 2022Object-Category Aware Reinforcement Learningcited by 6
  23. 2023Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Modelscited by 6
  24. 2025Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learningcited by 6
  25. 2025Object-Centric Representations Improve Policy Generalization in Robot Manipulationcited by 6
  26. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 6
  27. 2023Investigating the role of model-based learning in exploration and transfercited by 5
  28. 2024Slot Structured World Modelscited by 5
  29. 2023Predictive World Models from Real-World Partial Observationscited by 4
  30. 2023Relational Object-Centric Actor-Criticcited by 4
  31. 2024Compete and Compose: Learning Independent Mechanisms for Modular World Modelscited by 4
  32. 2024On Discovery of Local Independence over Continuous Variables via Neural Contextual Decompositioncited by 4
  33. 2025Object-Centric World Models for Causality-Aware Reinforcement Learningcited by 4
  34. 2025Is an object-centric representation beneficial for robotic manipulation ?cited by 3
  35. 2025SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Taskscited by 3
  36. 2022Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factorscited by 2
  37. 2023Object-Centric Scene Representations using Active Inferencecited by 2
  38. 2022Towards Improving the Generation Quality of Autoregressive Slot VAEscited by 1

50 most cited of 57 All 57 (JSON)