Object-Centric World Models Meet Monte Carlo Tree Search
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911366223233024 |
|---|---|
| author | Vakhitov, Rodion Ugadiarov, Leonid Panov, Aleksandr |
| author_facet | Vakhitov, Rodion Ugadiarov, Leonid Panov, Aleksandr |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_06604 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Object-Centric World Models Meet Monte Carlo Tree Search Vakhitov, Rodion Ugadiarov, Leonid Panov, Aleksandr Artificial Intelligence Machine Learning Robotics 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. |
| title | Object-Centric World Models Meet Monte Carlo Tree Search |
| topic | Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2601.06604 |