← Back to all news
arXiv Machine Learning By Donna Vakalis

The Intervention Gap in Latent World Models

Read the original on arXiv Machine Learning →

The paper introduces the concept of intervention fidelity in latent world models, measuring whether a model’s open‑loop transitions align with actual environment interventions. Experiments on TD‑MPC2, Cheetah, and DreamerV3 show that high reward fit does not guarantee fidelity, and that self‑supervised models can outperform task‑anchored ones in preserving intervention effects. The authors propose a capture‑gated audit to localize failures and argue that fidelity must be directly audited on the model’s native interface.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 9

Reward Observability and the Limits of Offline Checkpoint Selection in RSSM World Models

The paper investigates the closed‑loop behavior of a recurrent state‑space model (RSSM) trained on human demonstrations in LunarLander‑v3. Using the model for zero‑shot CEM MPC and actor‑critic training in imagination, the authors find that a model‑based A2C policy trained on a single checkpoint achieves returns comparable to the best model‑free A2C policy while requiring far fewer real transitions. They introduce the Reward Observability Fraction (ROF) to quantify how much of the reward gradient lies in the observable subspace of the latent dynamics, but show that ROF does not predict the collapse of MPC in offline settings, leaving the problem of predicting closed‑loop failure unresolved.

By Nikolai Smolyanskiy, Jonathan Shock
More like this →
arXiv Machine Learning
5d ago

One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models

The paper challenges the common practice of selecting latent world models based on one‑step prediction loss, arguing that this metric poorly predicts planning performance. Using a frozen‑decoder protocol, the authors decompose one‑step error into encoder‑inherent and predictor‑added components and evaluate goal‑conditioned planning across three continuous‑control environments. Their experiments show that improvements in one‑step fidelity do not correlate with planning success, with correlation coefficients near zero and inconsistent exchange rates across tasks.

By Joshua Cheung, Zhang He
ragreinforcement-learningfine-tuning
More like this →
arXiv AI
Sep 25

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

AD-WM is a new action‑discriminative joint‑embedding world model designed for counterfactual model predictive control. It augments residual latent dynamics with action‑recovery regularization based on inverse dynamics and conditional mutual information, while discarding auxiliary heads at test time so that MPC remains unchanged. Experiments on OGBench‑Cube and other simulation environments show substantial gains in hard‑start success and mean success, and zero‑shot transfer to a Franka robot improves pick‑and‑place success from 42.2% to 71.1%.

By Jiabin Qiu, Zixuan Chen, Hongye Cao, Jieqi Shi, Jing Huo, Yang Gao
rag
More like this →