Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control
The authors study how asynchronous action execution breaks the action semantics assumed by action-conditioned world-model controllers. They identify two architecture-dependent failure modes: TD-MPC2 suffers from a future-action timeline mismatch, while DreamerV3 can attribute transitions to previous actions that were not actually applied. They propose two execution-consistent interfaces—Future-Sequence and Applied-Action Feedback—that correct these mismatches without modifying pretrained world models.
