Matches in SemOpenAlex for { <https://semopenalex.org/work/W2077671246> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2077671246 endingPage "990" @default.
- W2077671246 startingPage "978" @default.
- W2077671246 abstract "In a multiagent system, if agents' experiences could be accessible and assessed between peers for environmental modeling, they can alleviate the burden of exploration for unvisited states or unseen situations so as to accelerate the learning process. Since how to build up an effective and accurate model within a limited time is an important issue, especially for complex environments, this paper introduces a model-based reinforcement learning method based on a tree structure to achieve efficient modeling and less memory consumption. The proposed algorithm tailored a Dyna-Q architecture to multiagent systems by means of a tree structure for modeling. The tree-model built from real experiences is used to generate virtual experiences such that the elapsed time in learning could be reduced. As well, this model is suitable for knowledge sharing. This paper is inspired by the concept of knowledge sharing methods in multiagent systems where an agent could construct a global model from scattered local models held by individual agents. Consequently, it can increase modeling accuracy so as to provide valid simulated experiences for indirect learning at the early stage of learning. To simplify the sharing process, the proposed method applies resampling techniques to grafting partial branches of trees containing required and useful experiences disseminated from experienced peers, instead of merging the whole trees. The simulation results demonstrate that the proposed sharing method can achieve the objectives of sample efficiency and learning acceleration in multiagent cooperation applications." @default.
- W2077671246 created "2016-06-24" @default.
- W2077671246 creator A5001081733 @default.
- W2077671246 creator A5061189209 @default.
- W2077671246 creator A5064655192 @default.
- W2077671246 date "2015-05-01" @default.
- W2077671246 modified "2023-09-30" @default.
- W2077671246 title "Model Learning and Knowledge Sharing for a Multiagent System With Dyna-Q Learning" @default.
- W2077671246 cites W1591808955 @default.
- W2077671246 cites W1970391951 @default.
- W2077671246 cites W1997733123 @default.
- W2077671246 cites W1997880753 @default.
- W2077671246 cites W2008809493 @default.
- W2077671246 cites W2022795107 @default.
- W2077671246 cites W2078196735 @default.
- W2077671246 cites W2095989982 @default.
- W2077671246 cites W2099618002 @default.
- W2077671246 cites W2124716489 @default.
- W2077671246 cites W2135765924 @default.
- W2077671246 cites W2147319420 @default.
- W2077671246 cites W2963302368 @default.
- W2077671246 cites W32403112 @default.
- W2077671246 doi "https://doi.org/10.1109/tcyb.2014.2341582" @default.
- W2077671246 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/25122850" @default.
- W2077671246 hasPublicationYear "2015" @default.
- W2077671246 type Work @default.
- W2077671246 sameAs 2077671246 @default.
- W2077671246 citedByCount "20" @default.
- W2077671246 countsByYear W20776712462017 @default.
- W2077671246 countsByYear W20776712462018 @default.
- W2077671246 countsByYear W20776712462019 @default.
- W2077671246 countsByYear W20776712462020 @default.
- W2077671246 countsByYear W20776712462021 @default.
- W2077671246 countsByYear W20776712462022 @default.
- W2077671246 countsByYear W20776712462023 @default.
- W2077671246 crossrefType "journal-article" @default.
- W2077671246 hasAuthorship W2077671246A5001081733 @default.
- W2077671246 hasAuthorship W2077671246A5061189209 @default.
- W2077671246 hasAuthorship W2077671246A5064655192 @default.
- W2077671246 hasConcept C111919701 @default.
- W2077671246 hasConcept C113174947 @default.
- W2077671246 hasConcept C119857082 @default.
- W2077671246 hasConcept C134306372 @default.
- W2077671246 hasConcept C154945302 @default.
- W2077671246 hasConcept C162319229 @default.
- W2077671246 hasConcept C163797641 @default.
- W2077671246 hasConcept C199360897 @default.
- W2077671246 hasConcept C2776604539 @default.
- W2077671246 hasConcept C2780801425 @default.
- W2077671246 hasConcept C33923547 @default.
- W2077671246 hasConcept C41008148 @default.
- W2077671246 hasConcept C41550386 @default.
- W2077671246 hasConcept C56739046 @default.
- W2077671246 hasConcept C97541855 @default.
- W2077671246 hasConcept C98045186 @default.
- W2077671246 hasConceptScore W2077671246C111919701 @default.
- W2077671246 hasConceptScore W2077671246C113174947 @default.
- W2077671246 hasConceptScore W2077671246C119857082 @default.
- W2077671246 hasConceptScore W2077671246C134306372 @default.
- W2077671246 hasConceptScore W2077671246C154945302 @default.
- W2077671246 hasConceptScore W2077671246C162319229 @default.
- W2077671246 hasConceptScore W2077671246C163797641 @default.
- W2077671246 hasConceptScore W2077671246C199360897 @default.
- W2077671246 hasConceptScore W2077671246C2776604539 @default.
- W2077671246 hasConceptScore W2077671246C2780801425 @default.
- W2077671246 hasConceptScore W2077671246C33923547 @default.
- W2077671246 hasConceptScore W2077671246C41008148 @default.
- W2077671246 hasConceptScore W2077671246C41550386 @default.
- W2077671246 hasConceptScore W2077671246C56739046 @default.
- W2077671246 hasConceptScore W2077671246C97541855 @default.
- W2077671246 hasConceptScore W2077671246C98045186 @default.
- W2077671246 hasIssue "5" @default.
- W2077671246 hasLocation W20776712461 @default.
- W2077671246 hasLocation W20776712462 @default.
- W2077671246 hasOpenAccess W2077671246 @default.
- W2077671246 hasPrimaryLocation W20776712461 @default.
- W2077671246 hasRelatedWork W2046669581 @default.
- W2077671246 hasRelatedWork W2091272629 @default.
- W2077671246 hasRelatedWork W2355247546 @default.
- W2077671246 hasRelatedWork W2379488605 @default.
- W2077671246 hasRelatedWork W2907306720 @default.
- W2077671246 hasRelatedWork W2961085424 @default.
- W2077671246 hasRelatedWork W3074294383 @default.
- W2077671246 hasRelatedWork W4206669594 @default.
- W2077671246 hasRelatedWork W4290840295 @default.
- W2077671246 hasRelatedWork W4319083788 @default.
- W2077671246 hasVolume "45" @default.
- W2077671246 isParatext "false" @default.
- W2077671246 isRetracted "false" @default.
- W2077671246 magId "2077671246" @default.
- W2077671246 workType "article" @default.