Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287194036> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4287194036 abstract "Multi-agent reinforcement learning methods have shown remarkable potential in solving complex multi-agent problems but mostly lack theoretical guarantees. Recently, mean field control and mean field games have been established as a tractable solution for large-scale multi-agent problems with many agents. In this work, driven by a motivating scheduling problem, we consider a discrete-time mean field control model with common environment states. We rigorously establish approximate optimality as the number of agents grows in the finite agent case and find that a dynamic programming principle holds, resulting in the existence of an optimal stationary policy. As exact solutions are difficult in general due to the resulting continuous action space of the limiting mean field Markov decision process, we apply established deep reinforcement learning methods to solve the associated mean field control problem. The performance of the learned mean field control policy is compared to typical multi-agent reinforcement learning approaches and is found to converge to the mean field performance for sufficiently many agents, verifying the obtained theoretical results and reaching competitive solutions." @default.
- W4287194036 created "2022-07-25" @default.
- W4287194036 creator A5070544702 @default.
- W4287194036 creator A5072604546 @default.
- W4287194036 creator A5075382536 @default.
- W4287194036 creator A5082267036 @default.
- W4287194036 date "2021-04-30" @default.
- W4287194036 modified "2023-10-18" @default.
- W4287194036 title "Discrete-Time Mean Field Control with Environment States" @default.
- W4287194036 doi "https://doi.org/10.48550/arxiv.2104.14900" @default.
- W4287194036 hasPublicationYear "2021" @default.
- W4287194036 type Work @default.
- W4287194036 citedByCount "0" @default.
- W4287194036 crossrefType "posted-content" @default.
- W4287194036 hasAuthorship W4287194036A5070544702 @default.
- W4287194036 hasAuthorship W4287194036A5072604546 @default.
- W4287194036 hasAuthorship W4287194036A5075382536 @default.
- W4287194036 hasAuthorship W4287194036A5082267036 @default.
- W4287194036 hasBestOaLocation W42871940361 @default.
- W4287194036 hasConcept C105795698 @default.
- W4287194036 hasConcept C106189395 @default.
- W4287194036 hasConcept C121332964 @default.
- W4287194036 hasConcept C126255220 @default.
- W4287194036 hasConcept C154945302 @default.
- W4287194036 hasConcept C159886148 @default.
- W4287194036 hasConcept C202213908 @default.
- W4287194036 hasConcept C202444582 @default.
- W4287194036 hasConcept C206729178 @default.
- W4287194036 hasConcept C33923547 @default.
- W4287194036 hasConcept C37404715 @default.
- W4287194036 hasConcept C41008148 @default.
- W4287194036 hasConcept C62520636 @default.
- W4287194036 hasConcept C91575142 @default.
- W4287194036 hasConcept C9652623 @default.
- W4287194036 hasConcept C97541855 @default.
- W4287194036 hasConceptScore W4287194036C105795698 @default.
- W4287194036 hasConceptScore W4287194036C106189395 @default.
- W4287194036 hasConceptScore W4287194036C121332964 @default.
- W4287194036 hasConceptScore W4287194036C126255220 @default.
- W4287194036 hasConceptScore W4287194036C154945302 @default.
- W4287194036 hasConceptScore W4287194036C159886148 @default.
- W4287194036 hasConceptScore W4287194036C202213908 @default.
- W4287194036 hasConceptScore W4287194036C202444582 @default.
- W4287194036 hasConceptScore W4287194036C206729178 @default.
- W4287194036 hasConceptScore W4287194036C33923547 @default.
- W4287194036 hasConceptScore W4287194036C37404715 @default.
- W4287194036 hasConceptScore W4287194036C41008148 @default.
- W4287194036 hasConceptScore W4287194036C62520636 @default.
- W4287194036 hasConceptScore W4287194036C91575142 @default.
- W4287194036 hasConceptScore W4287194036C9652623 @default.
- W4287194036 hasConceptScore W4287194036C97541855 @default.
- W4287194036 hasLocation W42871940361 @default.
- W4287194036 hasOpenAccess W4287194036 @default.
- W4287194036 hasPrimaryLocation W42871940361 @default.
- W4287194036 hasRelatedWork W1511927616 @default.
- W4287194036 hasRelatedWork W1994682696 @default.
- W4287194036 hasRelatedWork W2000918024 @default.
- W4287194036 hasRelatedWork W2008028818 @default.
- W4287194036 hasRelatedWork W2156021013 @default.
- W4287194036 hasRelatedWork W2161367706 @default.
- W4287194036 hasRelatedWork W2169203366 @default.
- W4287194036 hasRelatedWork W3181585847 @default.
- W4287194036 hasRelatedWork W3198564127 @default.
- W4287194036 hasRelatedWork W283149859 @default.
- W4287194036 isParatext "false" @default.
- W4287194036 isRetracted "false" @default.
- W4287194036 workType "article" @default.