What is recorded here?
Represented return laws by uniformly weighted learned quantile locations and used quantile regression updates, connecting approximation to a Wasserstein-minimizing projection.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
Uses inherited quantile regression, not its invention. Source Proposition2 contracts the quantile-projected fixed-policy Bellman operator in maximal infinity-Wasserstein distance for countable state/action spaces; not arbitrary neural greedy-control convergence or contraction in every finite-p Wasserstein metric. Empirical sample-Wasserstein loss itself can have biased minimizers.
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
Will Dabney; Mark Rowland; Marc G. Bellemare; Rémi Munos
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
QR-DQN: quantile-projected distributional value learning
Represented return laws by uniformly weighted learned quantile locations and used quantile regression updates, connecting approximation to a Wasserstein-minimizing projection.
Scientific scope
Uses inherited quantile regression, not its invention. Source Proposition2 contracts the quantile-projected fixed-policy Bellman operator in maximal infinity-Wasserstein distance for countable state/action spaces; not arbitrary neural greedy-control convergence or contraction in every finite-p Wasserstein metric. Empirical sample-Wasserstein loss itself can have biased minimizers.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Will Dabney; Mark Rowland; Marc G. Bellemare; Rémi Munos
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.