Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912779783> ?p ?o ?g. }
- W2912779783 endingPage "1495" @default.
- W2912779783 startingPage "1486" @default.
- W2912779783 abstract "We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structural relationship between policies and value functions including the line theorem, which shows that the value functions of policies constrained on all but one state describe a line segment. Finally, we use this novel perspective to introduce visualizations to enhance the understanding of the dynamics of reinforcement learning algorithms." @default.
- W2912779783 created "2019-02-21" @default.
- W2912779783 creator A5001087292 @default.
- W2912779783 creator A5010575626 @default.
- W2912779783 creator A5043577372 @default.
- W2912779783 creator A5067427868 @default.
- W2912779783 creator A5071583471 @default.
- W2912779783 date "2019-05-24" @default.
- W2912779783 modified "2023-10-01" @default.
- W2912779783 title "The Value Function Polytope in Reinforcement Learning" @default.
- W2912779783 hasPublicationYear "2019" @default.
- W2912779783 type Work @default.
- W2912779783 sameAs 2912779783 @default.
- W2912779783 citedByCount "11" @default.
- W2912779783 countsByYear W29127797832019 @default.
- W2912779783 countsByYear W29127797832020 @default.
- W2912779783 countsByYear W29127797832021 @default.
- W2912779783 countsByYear W29127797832022 @default.
- W2912779783 crossrefType "proceedings-article" @default.
- W2912779783 hasAuthorship W2912779783A5001087292 @default.
- W2912779783 hasAuthorship W2912779783A5010575626 @default.
- W2912779783 hasAuthorship W2912779783A5043577372 @default.
- W2912779783 hasAuthorship W2912779783A5067427868 @default.
- W2912779783 hasAuthorship W2912779783A5071583471 @default.
- W2912779783 hasConcept C105795698 @default.
- W2912779783 hasConcept C106189395 @default.
- W2912779783 hasConcept C111919701 @default.
- W2912779783 hasConcept C11413529 @default.
- W2912779783 hasConcept C118615104 @default.
- W2912779783 hasConcept C119857082 @default.
- W2912779783 hasConcept C126255220 @default.
- W2912779783 hasConcept C12713177 @default.
- W2912779783 hasConcept C14036430 @default.
- W2912779783 hasConcept C145691206 @default.
- W2912779783 hasConcept C14646407 @default.
- W2912779783 hasConcept C154945302 @default.
- W2912779783 hasConcept C159886148 @default.
- W2912779783 hasConcept C198352243 @default.
- W2912779783 hasConcept C2524010 @default.
- W2912779783 hasConcept C2776291640 @default.
- W2912779783 hasConcept C2778572836 @default.
- W2912779783 hasConcept C33923547 @default.
- W2912779783 hasConcept C41008148 @default.
- W2912779783 hasConcept C48103436 @default.
- W2912779783 hasConcept C72434380 @default.
- W2912779783 hasConcept C78458016 @default.
- W2912779783 hasConcept C80444323 @default.
- W2912779783 hasConcept C86803240 @default.
- W2912779783 hasConcept C97541855 @default.
- W2912779783 hasConcept C98763669 @default.
- W2912779783 hasConceptScore W2912779783C105795698 @default.
- W2912779783 hasConceptScore W2912779783C106189395 @default.
- W2912779783 hasConceptScore W2912779783C111919701 @default.
- W2912779783 hasConceptScore W2912779783C11413529 @default.
- W2912779783 hasConceptScore W2912779783C118615104 @default.
- W2912779783 hasConceptScore W2912779783C119857082 @default.
- W2912779783 hasConceptScore W2912779783C126255220 @default.
- W2912779783 hasConceptScore W2912779783C12713177 @default.
- W2912779783 hasConceptScore W2912779783C14036430 @default.
- W2912779783 hasConceptScore W2912779783C145691206 @default.
- W2912779783 hasConceptScore W2912779783C14646407 @default.
- W2912779783 hasConceptScore W2912779783C154945302 @default.
- W2912779783 hasConceptScore W2912779783C159886148 @default.
- W2912779783 hasConceptScore W2912779783C198352243 @default.
- W2912779783 hasConceptScore W2912779783C2524010 @default.
- W2912779783 hasConceptScore W2912779783C2776291640 @default.
- W2912779783 hasConceptScore W2912779783C2778572836 @default.
- W2912779783 hasConceptScore W2912779783C33923547 @default.
- W2912779783 hasConceptScore W2912779783C41008148 @default.
- W2912779783 hasConceptScore W2912779783C48103436 @default.
- W2912779783 hasConceptScore W2912779783C72434380 @default.
- W2912779783 hasConceptScore W2912779783C78458016 @default.
- W2912779783 hasConceptScore W2912779783C80444323 @default.
- W2912779783 hasConceptScore W2912779783C86803240 @default.
- W2912779783 hasConceptScore W2912779783C97541855 @default.
- W2912779783 hasConceptScore W2912779783C98763669 @default.
- W2912779783 hasLocation W29127797831 @default.
- W2912779783 hasOpenAccess W2912779783 @default.
- W2912779783 hasPrimaryLocation W29127797831 @default.
- W2912779783 hasRelatedWork W1528847347 @default.
- W2912779783 hasRelatedWork W1762265219 @default.
- W2912779783 hasRelatedWork W1786935204 @default.
- W2912779783 hasRelatedWork W1818181853 @default.
- W2912779783 hasRelatedWork W1866509886 @default.
- W2912779783 hasRelatedWork W2074862754 @default.
- W2912779783 hasRelatedWork W2075194013 @default.
- W2912779783 hasRelatedWork W2121863487 @default.
- W2912779783 hasRelatedWork W2145339207 @default.
- W2912779783 hasRelatedWork W2191938486 @default.
- W2912779783 hasRelatedWork W2592206372 @default.
- W2912779783 hasRelatedWork W2950533301 @default.
- W2912779783 hasRelatedWork W2953045501 @default.
- W2912779783 hasRelatedWork W2953365440 @default.
- W2912779783 hasRelatedWork W3035101501 @default.
- W2912779783 hasRelatedWork W3037025409 @default.
- W2912779783 hasRelatedWork W3041325747 @default.
- W2912779783 hasRelatedWork W3116293005 @default.
- W2912779783 hasRelatedWork W3148465953 @default.