mlsanityData to 14 Oct 2026

Object-Centric World Models Meet Monte Carlo Tree Search

arXiv 2601.06604 ↗First posted 10 Jan 2026cs.AI cs.LG cs.ROcited by 1

On the map: World models → Latent predictive world models

also in 1 more
Abstract (arXiv)

In this paper, we introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments more effectively. Unlike traditional approaches that process the world as a single undifferentiated input, our method employs Graph Neural Networks (GNNs) to capture intricate interactions among multiple objects. These objects, which can be manipulated and interact with each other, serve as the foundation for our model's understanding of the environment. We trained the algorithm in a complex setting teeming with diverse, interactive objects, demonstrating its ability to effectively learn and predict object dynamics. Our results highlight that a structured world model operating on object-centric representations can be successfully integrated into a model-based RL algorithm utilizing Monte Carlo Tree Search as a planning module.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Latent predictive world models, one of 11 directions in World models. Builds on 33 of its 40 references that are in the map. First posted on arXiv 10 Jan 2026.

Builds on

33 of 40 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning27 Jan
  2. 2023Relational Object-Centric Actor-Critic26 Oct
  3. 2021Conditional Object-Centric Learning from Video24 Nov
  4. 2019Contrastive Learning of Structured World Models27 Nov
  5. 2018Learning Latent Dynamics for Planning from Pixels12 Nov

Other references · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2017Neural Discrete Representation Learningcited by 4,712
  4. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  5. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  6. 2023Mastering Diverse Domains through World Modelscited by 1,253
  7. 2020Object-Centric Learning with Slot Attentioncited by 876
  8. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  9. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  10. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  11. 2021Deep ViT Features as Dense Visual Descriptorscited by 330
  12. 2021Mastering Atari Games with Limited Datacited by 237
16 more
  1. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  2. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 166
  3. 2021Illiterate DALL-E Learns to Composecited by 147
  4. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  5. 2015Model Predictive Path Integral Control using Covariance Variable Importance Samplingcited by 124
  6. 2020CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learningcited by 109
  7. 2023Object-Centric Slot Diffusioncited by 90
  8. 2023STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learningcited by 89
  9. 2019COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Explorationcited by 57
  10. 2017Deep Object-Centric Representations for Generalizable Robot Learningcited by 50
  11. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  12. 2024EfficientZero V2: Mastering Discrete and Continuous Control with Limited Datacited by 40
  13. 2022Learning to Generalize with Object-centric Agents in the Open World Survival Game Craftercited by 13
  14. 2023Object-Centric Learning with Slot Mixture Modulecited by 11
  15. 2023Spotlight Attention: Robust Object-Centric Learning With a Spatial Locality Priorcited by 8
  16. 2023Symmetry and Complexity in Object-Centric Deep Active Inference Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Latent State Design for World Models under Sufficiency Constraintscited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Interactive World Model for Object-Centric Reinforcement Learning
  2. 2024Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
  3. 2025Dyn-O: Building Structured World Models with Object-Centric Representations
  4. 2021Structured World Belief for Reinforcement Learning in POMDP
  5. 2026Causal Object-Centric Models for Planning with Monte Carlo Tree Search
  6. 2023Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
  7. 2026World-as-Graph: Relational World Modeling Through Latent Space Graphs
  8. 2025When Object-Centric World Models Meet Policy Learning: From Pixels to Policies, and Where It Breaks