Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
Classification
View four quadrants- Major category
- WAMs
- Quadrant
- Outside quadrants
- Architecture
- Pending verification
- Prediction paradigm
- Other mechanisms
- Subcategories
- Latent prediction & JEPAPolicy post-training & WM-RL
- Source review status
- Not assigned
Category review. A recurrent action-conditioned latent world model supports MPC search over imagined intervention futures and receding-horizon action execution; contrastive outcome training improves this specific planning system. The described action mechanism is external planning, model-assisted policy optimization, geometric tracking, or video-conditioned control; the source does not establish joint future/action generation or an IDM action decoder. Reading evidence
Contribution
Counterfactual Latent World Models (CLWM) train action-conditioned imagined futures to preserve differences in intervention outcomes even when observations look alike. A recurrent world model supplies latent rollouts to model-predictive control; privileged outcome labels supervise an additional contrastive objective during training. Reported simulation gains reach 11.6 percentage points in navigation success. The evidence supports targeted representation training, while supervision-matched controls and audits of pretrained encoders remain open.
Abstract
An abstract has not been added yet.
Affiliations
Harvard University