mlsanityData to 14 Oct 2026

Causal Object-Centric Models for Planning with Monte Carlo Tree Search

arXiv 2606.14418 ↗First posted 12 Jun 2026cs.AI cs.LG cs.ROcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

We introduce COMET (Causal Object-centric Model for Efficient Tree search), a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space. COMET pairs a frozen unsupervised object-centric encoder with a transformer-based world model, in which actions are bound to objects through a novel action-slot fusion mechanism that is used in slot transition prediction. Policy and value heads use object-causal attention, modulating token interactions by learned per-slot relevance scores so that decision-making concentrates on task-relevant entities. COMET adds an explicit object-level inductive bias to MuZero-style latent planning. Across eight visually and dynamically diverse tasks from the Object-Centric Visual RL benchmark, ManiSkill, Robosuite, and VizDoom, COMET achieves a higher mean normalized score during the early stages of training compared to object-centric and monolithic baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 8 of its 49 references that are in the map. First posted on arXiv 12 Jun 2026.

Builds on

8 of 49 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning27 Jan

Other references · 7

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018World Modelscited by 1,513
  3. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  4. 2021Deep ViT Features as Dense Visual Descriptorscited by 330
  5. 2019COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Explorationcited by 57
  6. 2024SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixelscited by 24
  7. 2022Binding Actions to Objects in World Modelscited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Object-Centric World Models for Causality-Aware Reinforcement Learning
  2. 2025Better Decisions through the Right Causal World Model
  3. 2026Object-Centric World Models Meet Monte Carlo Tree Search
  4. 2023Relational Object-Centric Actor-Critic
  5. 2026Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations
  6. 2024Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction
  7. 2021Structured World Belief for Reinforcement Learning in POMDP
  8. 2026Better Slots, Better Worlds: Representation Quality & Robustness in Object-Centric World Models