What is recorded here?
Combined conditional action-denoising behavior regularization with Q-value maximization, backpropagating the Q objective through the reverse diffusion chain and learning twin critics from offline transitions.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
The method learns single-action policies, not Diffuser's full-trajectory planner. Denoising-chain evaluation and differentiation cost remain; near-behavior regularization and benchmark gains are not universal safety or optimality guarantees. The preprint document is dated 15 August 2022, while its arXiv submission is dated 12 August 2022; these are different bibliographic dates.
Read the original work
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Zhendong Wang; Jonathan J Hunt; Mingyuan Zhou
Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Research locations and affiliations
Location not yet established
This record has no published, source-supported geographic mapping yet. Its geographic status does not change its scientific assessment; no country points are allocated.
English catalogue narrative
Diffusion-QL: Q-guided training of expressive diffusion action policies
Combined conditional action-denoising behavior regularization with Q-value maximization, backpropagating the Q objective through the reverse diffusion chain and learning twin critics from offline transitions.
Scientific scope
The method learns single-action policies, not Diffuser's full-trajectory planner. Denoising-chain evaluation and differentiation cost remain; near-behavior regularization and benchmark gains are not universal safety or optimality guarantees. The preprint document is dated 15 August 2022, while its arXiv submission is dated 12 August 2022; these are different bibliographic dates.
People and systems
Zhendong Wang; Jonathan J Hunt; Mingyuan Zhou