<ul><li>Reinforcement learning agents often exploit spurious correlations in training data, resulting in brittle behaviors that fail to generalize to new environments.</li><li>The Causal Object-centric Model Extraction Tool (COMET) is an algorithm designed to learn interpretable causal world models (CWMs).</li><li>COMET extracts object-centric state descriptions from observations and models object-centric transitions using symbolic regression.</li><li>COMET constructs CWMs that align with the true causal structure of the environment, enabling better planning and decision-making in reinforcement learning.</li></ul>

Better Decisions through the Right Causal World Model

Discover more