Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
This work introduces Counterfactual Latent World Models (CLWM), which combine a recurrent belief-state encoder, action-conditioned latent dynamics, and a contrastive counterfactual objective that separates futures induced by distinct interventions even when their observations look alike.
Todd Y. Zhou, Daniella Zhang
· 0 citations