No AI summary available for this article.
Why It Matters
Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Latent world models are typically trained to predict factual transitions, whereas model predictive control (MPC) must compare alternative actions from the same state. A model can therefore achieve low factual prediction error yet poorly distinguish candidate actions. We introduce AD-WM, an action-discriminative joint-embedding world model for counterfactual MPC. AD-WM combines residual latent dynamics with predictor-level action-recovery regularization, using inverse dynamics and a normalized recovery objective motivated by conditional mutual information. Both objectives encourage planning tra...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.30264v1 · Indexed about 1 hour ago