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

• URL: http://arxiv.org/abs/2606.14418v1
• Date: Fri, 12 Jun 2026 12:55:25 GMT
• Title: Causal Object-Centric Models for Planning with Monte Carlo Tree Search
• Abstract summary: COMET is a model-based reinforcement learning algorithm that performs Monte Carlo Tree Search in a slot-structured latent space.<n>Policy and value heads use object-causal attention, modulating token interactions by learned per-slot relevance scores.<n> COMET achieves a higher mean normalized score during the early stages of training compared to object-centric and monolithic baselines.
• Score: 49.61977404247856
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Object-Centric World Models Meet Monte Carlo Tree Search [49.12393425510251]
  We introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments.<n>Our method employs Graph Neural Networks (GNNs) to capture intricate interactions among multiple objects.<n>We trained the algorithm in a complex setting teeming with diverse, interactive objects, demonstrating its ability to effectively learn and predict object dynamics.
  arXiv  Detail & Related papers  (2026-01-10T15:59:17Z)
• Slot Structured World Models [0.0]
  State-of-the-art approaches use a feedforward encoder to extract object embeddings and a latent graph neural network to model the interaction between these object embeddings. We introduce it Slot Structured World Models (SSWM), a class of world models that combines an it object-centric encoder with a latent graph-based dynamics model.
  arXiv  Detail & Related papers  (2024-01-08T21:19:30Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• An Object SLAM Framework for Association, Mapping, and High-Level Tasks [12.62957558651032]
  We present a comprehensive object SLAM framework that focuses on object-based perception and object-oriented robot tasks. A range of public datasets and real-world results have been used to evaluate the proposed object SLAM framework for its efficient performance.
  arXiv  Detail & Related papers  (2023-05-12T08:10:14Z)
• Detecting Human-Object Interactions with Object-Guided Cross-Modal Calibrated Semantics [6.678312249123534]
  We aim to boost end-to-end models with object-guided statistical priors. We propose to utilize a Verb Semantic Model (VSM) and use semantic aggregation to profit from this object-guided hierarchy. The above modules combined composes Object-guided Cross-modal Network (OCN)
  arXiv  Detail & Related papers  (2022-02-01T07:39:04Z)
• SORNet: Spatial Object-Centric Representations for Sequential Manipulation [39.88239245446054]
  Sequential manipulation tasks require a robot to perceive the state of an environment and plan a sequence of actions leading to a desired goal state. We propose SORNet, which extracts object-centric representations from RGB images conditioned on canonical views of the objects of interest.
  arXiv  Detail & Related papers  (2021-09-08T19:36:29Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)
• Look-into-Object: Self-supervised Structure Modeling for Object Recognition [71.68524003173219]
  We propose to "look into object" (explicitly yet intrinsically model the object structure) through incorporating self-supervisions. We show the recognition backbone can be substantially enhanced for more robust representation learning. Our approach achieves large performance gain on a number of benchmarks, including generic object recognition (ImageNet) and fine-grained object recognition tasks (CUB, Cars, Aircraft)
  arXiv  Detail & Related papers  (2020-03-31T12:22:51Z)
• A Unified Object Motion and Affinity Model for Online Multi-Object Tracking [127.5229859255719]
  We propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA. UMA integrates single object tracking and metric learning into a unified triplet network by means of multi-task learning. We equip our model with a task-specific attention module, which is used to boost task-aware feature learning.
  arXiv  Detail & Related papers  (2020-03-25T09:36:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.