paper-with-me

홈 › Papers

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

2026-06-12 · Rodion Vakhitov, Leonid Ugadiarov, Alexey Skrynnik, Aleksandr Panov 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.

📄 PDF Abstract BibTeX arXiv:2606.14418

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Object-Centric World Models Meet Monte Carlo Tree Search

2026-01-10 · Rodion Vakhitov, Leonid Ugadiarov, Aleksandr Panov 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…

Reinforcement Learning

Monte Carlo Planning for Stochastic Control on Constrained Markov Decision Processes

2024-06-23 · Larkin Liu, Shiqi Liu, Matej Jusup

In the world of stochastic control, especially in economics and engineering, Markov Decision Processes (MDPs) can effectively model various stochastic decision processes, from asset management to transportation optimizat…

Asset ManagementDisentanglement

Structured World Belief for Reinforcement Learning in POMDP

2021-07-19 · Gautam Singh, Skand Peri, Junghyun Kim, Hyunseok Kim 외

Object-centric world models provide structured representation of the scene and can be an important backbone in reinforcement learning and planning. However, existing approaches suffer in partially-observable environments…

Inductive BiasObjectObject Trackingreinforcement-learning+2

Convex Hull Monte-Carlo Tree Search

2020-03-09 · Michael Painter, Bruno Lacerda, Nick Hawes

This work investigates Monte-Carlo planning for agents in stochastic environments, with multiple objectives. We propose the Convex Hull Monte-Carlo Tree-Search (CHMCTS) framework, which builds upon Trial Based Heuristic …

Multi-Armed Bandits

Probabilistic Planning with Sequential Monte Carlo methods

2019-05-01 · ICLR 2019 5 · Alexandre Piche, Valentin Thomas, Cyril Ibrahim, Yoshua Bengio 외

In this work, we propose a novel formulation of planning which views it as a probabilistic inference problem over future optimal trajectories. This enables us to use sampling methods, and thus, tackle planning in continu…

continuous-controlContinuous Control