RESEARCH PAPERYear 2024

World Models via Policy-Guided Trajectory Diffusion

Marc Rigter; Jun Yamada; Ingmar Posner

Classification

View four quadrants
Major category
Foundational work
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. PolyGRAD is a 2024 general model-based RL mechanism that couples trajectory diffusion with a separate policy to generate approximately on-policy synthetic experience. Its role is foundational imagination-based training, not a task-specific WAM inference architecture. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX