Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894069784> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2894069784 abstract "This paper proposes Cooperative and competitive Reinforcement And Imitation Learning (CRAIL) for selecting an appropriate policy from a set of multiple heterogeneous modules and training all of them in parallel. Each learning module has its own network architecture and improves the policy based on an off-policy reinforcement learning algorithm and behavior cloning from samples collected by a behavior policy that is constructed by a combination of all the policies. Since the mixing weights are determined by the performance of the module, a better policy is automatically selected based on the learning progress. Experimental results on a benchmark control task show that CRAIL successfully achieves fast learning by allowing modules with complicated network structures to exploit task-relevant samples for training." @default.
- W2894069784 created "2018-10-05" @default.
- W2894069784 creator A5031054137 @default.
- W2894069784 date "2018-09-27" @default.
- W2894069784 modified "2023-09-23" @default.
- W2894069784 title "Cooperative and Competitive Reinforcement and Imitation Learning for a Mixture of Heterogeneous Learning Modules" @default.
- W2894069784 cites W1977655452 @default.
- W2894069784 cites W2012036715 @default.
- W2894069784 cites W2109910161 @default.
- W2894069784 cites W2119717200 @default.
- W2894069784 cites W2145339207 @default.
- W2894069784 cites W2146957157 @default.
- W2894069784 cites W2156174987 @default.
- W2894069784 cites W2167647761 @default.
- W2894069784 cites W2168342951 @default.
- W2894069784 cites W2257979135 @default.
- W2894069784 cites W2754517384 @default.
- W2894069784 cites W2766447205 @default.
- W2894069784 cites W2788862220 @default.
- W2894069784 cites W2795561664 @default.
- W2894069784 cites W2962834855 @default.
- W2894069784 cites W2963099939 @default.
- W2894069784 cites W32403112 @default.
- W2894069784 doi "https://doi.org/10.3389/fnbot.2018.00061" @default.
- W2894069784 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6170616" @default.
- W2894069784 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30319389" @default.
- W2894069784 hasPublicationYear "2018" @default.
- W2894069784 type Work @default.
- W2894069784 sameAs 2894069784 @default.
- W2894069784 citedByCount "8" @default.
- W2894069784 countsByYear W28940697842019 @default.
- W2894069784 countsByYear W28940697842020 @default.
- W2894069784 countsByYear W28940697842021 @default.
- W2894069784 countsByYear W28940697842022 @default.
- W2894069784 countsByYear W28940697842023 @default.
- W2894069784 crossrefType "journal-article" @default.
- W2894069784 hasAuthorship W2894069784A5031054137 @default.
- W2894069784 hasBestOaLocation W28940697841 @default.
- W2894069784 hasConcept C119857082 @default.
- W2894069784 hasConcept C120822770 @default.
- W2894069784 hasConcept C126388530 @default.
- W2894069784 hasConcept C13280743 @default.
- W2894069784 hasConcept C154945302 @default.
- W2894069784 hasConcept C15744967 @default.
- W2894069784 hasConcept C162324750 @default.
- W2894069784 hasConcept C165696696 @default.
- W2894069784 hasConcept C177264268 @default.
- W2894069784 hasConcept C185798385 @default.
- W2894069784 hasConcept C187736073 @default.
- W2894069784 hasConcept C199360897 @default.
- W2894069784 hasConcept C205649164 @default.
- W2894069784 hasConcept C2775924081 @default.
- W2894069784 hasConcept C2780451532 @default.
- W2894069784 hasConcept C38652104 @default.
- W2894069784 hasConcept C41008148 @default.
- W2894069784 hasConcept C77805123 @default.
- W2894069784 hasConcept C8038995 @default.
- W2894069784 hasConcept C97541855 @default.
- W2894069784 hasConceptScore W2894069784C119857082 @default.
- W2894069784 hasConceptScore W2894069784C120822770 @default.
- W2894069784 hasConceptScore W2894069784C126388530 @default.
- W2894069784 hasConceptScore W2894069784C13280743 @default.
- W2894069784 hasConceptScore W2894069784C154945302 @default.
- W2894069784 hasConceptScore W2894069784C15744967 @default.
- W2894069784 hasConceptScore W2894069784C162324750 @default.
- W2894069784 hasConceptScore W2894069784C165696696 @default.
- W2894069784 hasConceptScore W2894069784C177264268 @default.
- W2894069784 hasConceptScore W2894069784C185798385 @default.
- W2894069784 hasConceptScore W2894069784C187736073 @default.
- W2894069784 hasConceptScore W2894069784C199360897 @default.
- W2894069784 hasConceptScore W2894069784C205649164 @default.
- W2894069784 hasConceptScore W2894069784C2775924081 @default.
- W2894069784 hasConceptScore W2894069784C2780451532 @default.
- W2894069784 hasConceptScore W2894069784C38652104 @default.
- W2894069784 hasConceptScore W2894069784C41008148 @default.
- W2894069784 hasConceptScore W2894069784C77805123 @default.
- W2894069784 hasConceptScore W2894069784C8038995 @default.
- W2894069784 hasConceptScore W2894069784C97541855 @default.
- W2894069784 hasLocation W28940697841 @default.
- W2894069784 hasLocation W28940697842 @default.
- W2894069784 hasLocation W28940697843 @default.
- W2894069784 hasLocation W28940697844 @default.
- W2894069784 hasLocation W28940697845 @default.
- W2894069784 hasOpenAccess W2894069784 @default.
- W2894069784 hasPrimaryLocation W28940697841 @default.
- W2894069784 hasRelatedWork W1509467138 @default.
- W2894069784 hasRelatedWork W3022038857 @default.
- W2894069784 hasRelatedWork W3136007272 @default.
- W2894069784 hasRelatedWork W3166789302 @default.
- W2894069784 hasRelatedWork W3183432322 @default.
- W2894069784 hasRelatedWork W4285070106 @default.
- W2894069784 hasRelatedWork W4286750964 @default.
- W2894069784 hasRelatedWork W4286899287 @default.
- W2894069784 hasRelatedWork W4289543317 @default.
- W2894069784 hasRelatedWork W4319083788 @default.
- W2894069784 hasVolume "12" @default.
- W2894069784 isParatext "false" @default.
- W2894069784 isRetracted "false" @default.
- W2894069784 magId "2894069784" @default.
- W2894069784 workType "article" @default.