DTRC：面向离线视觉控制的有向时间表征

View PDF HTML (experimental)

Abstract:Predictive world models provide compact visual representations for control. Control requires a latent geometry aligned with temporal reachability rather than predictive similarity alone. We introduce Directed Temporal Representations for Control (DTRC), which learns such a geometry from offline visual trajectories on top of frozen LeWorldModel (LeWM) features. DTRC constructs a directed temporal quasimetric over the learned control representation. Short-range temporal offsets calibrate the distance scale. Bootstrapped targets extend temporal reachability across longer horizons. Action-conditioned consistency aligns the representation with local transition dynamics. The resulting distance estimates temporal reaching cost, and its change across a transition defines goal-relative temporal progress. We use this progress signal as a temporal critic for direct goal-conditioned policy learning. Model-assisted targets provide an additional training-time refinement under behavior-support and dynamics-agreement constraints. Across ten visual control tasks, DTRC achieves strong goal-conditioned control performance relative to planning and direct-policy baselines. Held-out diagnostics on the four LeWM tasks show consistent short-range temporal calibration, task-dependent long-range and directional structure, and positive transition-level progress. Temporal supervision improves the same flow-policy parameterization across all four LeWM tasks, while the resulting policy acts directly without iterative trajectory search at test time.

Subjects:	Machine Learning (cs.LG)
Cite as:	arXiv:2610.08960 [cs.LG]
	(or arXiv:2610.08960v1 [cs.LG] for this version)
	https://doi.org/10.48550/arXiv.2610.08960 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chenyang Yuan [view email]
[v1] Tue, 6 Oct 2026 18:26:53 UTC (33,832 KB)