Skip to content

AD-WM: Action-Discriminative World Models for Counterfactual Model Predictive Control

Sep 2026 · arXiv.org · Vol abs/2609.30264 · 2 citations · 34 references
Computer Science

TL;DR

AD-WM, an action-discriminative joint-embedding world model for counterfactual MPC, is introduced, which combines residual latent dynamics with predictor-level action-recovery regularization, using inverse dynamics and a normalized recovery objective motivated by conditional mutual information.

Abstract

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 transitions to preserve action information; their auxiliary heads are discarded at test time, leaving MPC unchanged. On OGBench-Cube, AD-WM improves hard-start success from 3.7% to 52.0% over a matched LeWM baseline and improves mean success over the reproduced baseline in four of five simulation environments. Planning diagnostics show that factual prediction error and whole-bank action ranking do not follow the closed-loop success ordering, whereas CEM-aligned elite regret tracks success more closely. With a frozen V-JEPA 2 encoder and matched DROID post-training, AD-WM also improves zero-shot transfer to our Franka setup, increasing basic pick-and-place success from 42.2% to 71.1% without lab-specific adaptation. These results suggest that world models for planning should preserve action-dependent differences needed for counterfactual selection, rather than optimize factual prediction accuracy alone. More videos and code are available at https://ad-wm.github.io/.

View source

Similar papers

Preprint Oct 2026

TwinJEPA: Action-Preferred Predictive Representations for Goal-Conditioned Control

The results suggest that local action-comparison supervision can complement temporal prediction by encouraging JEPA-based representations to retain both long-horizon temporal structure and fine-grained distinctions among locally observed actions for offline zero-shot control.

Fei-Ran You, Hong-Yang Du · 1 citation
#machine learning Preprint Sep 2026

JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts

World models enable agents to plan by predicting future states of the environment, but their predictions can become unreliable when test-time dynamics differ from those seen during training. We present JEPA-TTT, which adapts the latent dynamics predictor of a pretrained action-conditioned Joint-Embedding Predictive Arc...

Zheyuan Zhang, Su-Yu Ye, Nakul Agarwal et al. · 1 citation · ⚡1
#machine learning Preprint Oct 2026

When Low Prediction Error Misleads Planning: Diagnosing Representation, Dynamics, and Decision Failures in Latent World Models

The component that dominates a latent world model's prediction error need not be the one whose repair most improves action selection. We show this by comparing action sequences from identical physical starts and separating endpoint error into a candidate-pool center and action-relative responses. Across four model fami...

Rui Min, Xian-Yao Li, Fang Xu et al. · 1 citation
Preprint Aug 2026

Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning

Action-conditioned objectives improve the geometry used by Euclidean-cost, CEM-based latent MPC, and DA-LeWM augments LeWM with inverse-dynamics and demonstration-conditioned goal-action heads, and accelerates convergence and achieves higher online success than LeWM.

Jia-Wei Wang, Ke Rui, Yu-Shen Zuo et al. · 8 citations
#artificial intelligence Preprint Oct 2026

Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models

Action Consequence Alignment (ACA), a training objective that complements forward prediction by penalizing the prediction error advantage of locally searched alternatives over factual actions without additional model components or environment interactions during training, is introduced.

Jin-Ping Wang, Zhi-Qiang Gao, Xian-Tong Zhen et al. · 1 citation
#artificial intelligence Preprint Sep 2026

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

Related blog posts

MIT News · Artificial Intelligence Nov 13, 2026

Helping robots fit into the human workplace

Founded by Anthony Jules ’92, SM ’92 and Professor Emeritus Rodney Brooks, Robust AI’s robots are designed to collaborate with humans in factories and warehouses.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.