arXiv CS AI#tech
Causal Object-Centric Models for Planning with Monte Carlo Tree Searchtranslating…
Factuality: 90/100USACornell University
arXiv:2606.14418v1 Announce Type: new
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