arXiv:2611.14955v1 Announce Type: cross
Abstract: Model-based planners that roll out imagined futures assume the transition model faithfully propagates task-relevant signals—a property rarely measured directly. In a single-seed case study of a Recurrent State Space Model world model with active-inference planning in the CARLA driving simulator, we identify a \textbf{posterior-prior gap}—posterior (observation-filtered) states retain obstacle information that imagined rollout states progressively lose: a supervised obstacle probe achieves AUC 0.85 on posterior states, but the same probe applied to imagined prior states shows monotonic decay (AUC 0.85$\rightarrow$0.71 over 15 steps; logit separation drops 57\%). Because the probe is identical, the decay isolates the transition model—not the representation—as the information bottleneck. Obstacle avoidance drops to 0\% without privileged runtime coordinates, and the planner's own ensemble-based epistemic term does not flag the loss—ensemble disagreement yields AUC 0.52 as an obstacle classifier (chance level), making the failure an unflagged imagination failure—an unknown unknown at planning time. As a secondary contribution, we show that \textbf{task-conditioned weighting of Effective Free Energy components} over the same world model yields lane keeping ($81.2 \pm 1.8$\% route completion) and obstacle avoidance (28/28 avoided, \emph{using privileged coordinates}) in the CARLA simulator, with runtime weight modulation enabling post-evasion centering.
Abstract: Model-based planners that roll out imagined futures assume the transition model faithfully propagates task-relevant signals—a property rarely measured directly. In a single-seed case study of a Recurrent State Space Model world model with active-inference planning in the CARLA driving simulator, we identify a \textbf{posterior-prior gap}—posterior (observation-filtered) states retain obstacle information that imagined rollout states progressively lose: a supervised obstacle probe achieves AUC 0.85 on posterior states, but the same probe applied to imagined prior states shows monotonic decay (AUC 0.85$\rightarrow$0.71 over 15 steps; logit separation drops 57\%). Because the probe is identical, the decay isolates the transition model—not the representation—as the information bottleneck. Obstacle avoidance drops to 0\% without privileged runtime coordinates, and the planner's own ensemble-based epistemic term does not flag the loss—ensemble disagreement yields AUC 0.52 as an obstacle classifier (chance level), making the failure an unflagged imagination failure—an unknown unknown at planning time. As a secondary contribution, we show that \textbf{task-conditioned weighting of Effective Free Energy components} over the same world model yields lane keeping ($81.2 \pm 1.8$\% route completion) and obstacle avoidance (28/28 avoided, \emph{using privileged coordinates}) in the CARLA simulator, with runtime weight modulation enabling post-evasion centering.
This article has been indexed from cs.AI updates on arXiv.org
Read the original article:
The Posterior-Prior Epistemic Gap: When World Model Imagination Fails to Carry Task-Relevant Signals