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

Abstract

Latent world models are routinely selected, checkpointed and ablated on one-step prediction loss, on the assumption that a model which predicts the next latent better is a better model. In model-based RL this assumption is known to be unreliable; we ask whether it also fails for latent world models, where the training target is the model's own embedding and the loss is not expressed in interpretable units. We introduce a frozen-decoder protocol reporting one-step error in physical units, decomposed into the part already present in the encoder's representation and the part the predictor adds. Applying it to a recent end-to-end JEPA world model across three continuous-control environments, we move the metric by fine-tuning and measure goal-conditioned planning on the same checkpoints, with three training seeds and paired planning seeds throughout. Within one environment, a per-epoch ladder shows the relationship saturating after a single epoch: the first epoch improves fidelity by 32% and planning by 4.4 pp, but across the fifteen checkpoints that follow -- a further 15% fidelity improvement, monotone in every training seed -- the correlation between one-step error and planning success is r = -0.010. This is not a task-ceiling artifact: stratifying by a model-independent measure of training-data support, planning in the lowest-support stratum starts at 80%, leaving ample headroom, and is nonetheless flat from epoch 1 onward. Across environments the exchange rate is equally unstable: a 93% fidelity reduction on TwoRoom yields -0.7 pp of planning, while a 40% reduction on PushT yields +4.9 pp [+1.1, +8.9]. All results replicate under a decoder-free measure, latent drift. We also show that a matched continued-training control absorbs the entire fidelity gain we had attributed to an auxiliary objective.