Matches in SemOpenAlex for { <https://semopenalex.org/work/W2964615009> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W2964615009 abstract "In multitask reinforcement learning, tasks often have sub-tasks that share the same solution, even though the overall tasks are different. If the shared-portions could be effectively identified, then the learning process could be improved since all the samples between tasks in the shared space could be used. In this paper, we propose a Sharing Experience Framework (SEF) for simultaneously training of multiple tasks. In SEF, a confidence sharing agent uses task-specific rewards from the environment to identify similar parts that should be shared across tasks and defines those parts as shared-regions between tasks. The shared-regions are expected to guide task-policies sharing their experience during the learning process. The experiments highlight that our framework improves the performance and the stability of learning task-policies, and is possible to help task-policies avoid local optimums." @default.
- W2964615009 created "2019-08-13" @default.
- W2964615009 creator A5005900412 @default.
- W2964615009 creator A5021734821 @default.
- W2964615009 creator A5046379131 @default.
- W2964615009 creator A5047301024 @default.
- W2964615009 creator A5053574580 @default.
- W2964615009 creator A5053935756 @default.
- W2964615009 creator A5076195477 @default.
- W2964615009 creator A5085899126 @default.
- W2964615009 date "2019-08-01" @default.
- W2964615009 modified "2023-10-05" @default.
- W2964615009 title "Sharing Experience in Multitask Reinforcement Learning" @default.
- W2964615009 cites W1575592356 @default.
- W2964615009 cites W1771410628 @default.
- W2964615009 cites W1981437899 @default.
- W2964615009 cites W1995688924 @default.
- W2964615009 cites W2106261932 @default.
- W2964615009 cites W2145339207 @default.
- W2964615009 cites W2169743339 @default.
- W2964615009 cites W2173248099 @default.
- W2964615009 cites W2174786457 @default.
- W2964615009 cites W2294805292 @default.
- W2964615009 cites W2553882142 @default.
- W2964615009 cites W2739678353 @default.
- W2964615009 cites W2785342287 @default.
- W2964615009 cites W2964262254 @default.
- W2964615009 doi "https://doi.org/10.24963/ijcai.2019/505" @default.
- W2964615009 hasPublicationYear "2019" @default.
- W2964615009 type Work @default.
- W2964615009 sameAs 2964615009 @default.
- W2964615009 citedByCount "9" @default.
- W2964615009 countsByYear W29646150092020 @default.
- W2964615009 countsByYear W29646150092021 @default.
- W2964615009 countsByYear W29646150092022 @default.
- W2964615009 countsByYear W29646150092023 @default.
- W2964615009 crossrefType "proceedings-article" @default.
- W2964615009 hasAuthorship W2964615009A5005900412 @default.
- W2964615009 hasAuthorship W2964615009A5021734821 @default.
- W2964615009 hasAuthorship W2964615009A5046379131 @default.
- W2964615009 hasAuthorship W2964615009A5047301024 @default.
- W2964615009 hasAuthorship W2964615009A5053574580 @default.
- W2964615009 hasAuthorship W2964615009A5053935756 @default.
- W2964615009 hasAuthorship W2964615009A5076195477 @default.
- W2964615009 hasAuthorship W2964615009A5085899126 @default.
- W2964615009 hasBestOaLocation W29646150091 @default.
- W2964615009 hasConcept C107457646 @default.
- W2964615009 hasConcept C111919701 @default.
- W2964615009 hasConcept C112972136 @default.
- W2964615009 hasConcept C119857082 @default.
- W2964615009 hasConcept C154945302 @default.
- W2964615009 hasConcept C15744967 @default.
- W2964615009 hasConcept C162324750 @default.
- W2964615009 hasConcept C175154964 @default.
- W2964615009 hasConcept C187736073 @default.
- W2964615009 hasConcept C2777311342 @default.
- W2964615009 hasConcept C2778572836 @default.
- W2964615009 hasConcept C2780451532 @default.
- W2964615009 hasConcept C28006648 @default.
- W2964615009 hasConcept C41008148 @default.
- W2964615009 hasConcept C67203356 @default.
- W2964615009 hasConcept C77805123 @default.
- W2964615009 hasConcept C97541855 @default.
- W2964615009 hasConcept C98045186 @default.
- W2964615009 hasConceptScore W2964615009C107457646 @default.
- W2964615009 hasConceptScore W2964615009C111919701 @default.
- W2964615009 hasConceptScore W2964615009C112972136 @default.
- W2964615009 hasConceptScore W2964615009C119857082 @default.
- W2964615009 hasConceptScore W2964615009C154945302 @default.
- W2964615009 hasConceptScore W2964615009C15744967 @default.
- W2964615009 hasConceptScore W2964615009C162324750 @default.
- W2964615009 hasConceptScore W2964615009C175154964 @default.
- W2964615009 hasConceptScore W2964615009C187736073 @default.
- W2964615009 hasConceptScore W2964615009C2777311342 @default.
- W2964615009 hasConceptScore W2964615009C2778572836 @default.
- W2964615009 hasConceptScore W2964615009C2780451532 @default.
- W2964615009 hasConceptScore W2964615009C28006648 @default.
- W2964615009 hasConceptScore W2964615009C41008148 @default.
- W2964615009 hasConceptScore W2964615009C67203356 @default.
- W2964615009 hasConceptScore W2964615009C77805123 @default.
- W2964615009 hasConceptScore W2964615009C97541855 @default.
- W2964615009 hasConceptScore W2964615009C98045186 @default.
- W2964615009 hasLocation W29646150091 @default.
- W2964615009 hasOpenAccess W2964615009 @default.
- W2964615009 hasPrimaryLocation W29646150091 @default.
- W2964615009 hasRelatedWork W2084273017 @default.
- W2964615009 hasRelatedWork W2289004814 @default.
- W2964615009 hasRelatedWork W2784094750 @default.
- W2964615009 hasRelatedWork W2786916331 @default.
- W2964615009 hasRelatedWork W2961085424 @default.
- W2964615009 hasRelatedWork W4200580761 @default.
- W2964615009 hasRelatedWork W4319083788 @default.
- W2964615009 hasRelatedWork W4319309271 @default.
- W2964615009 hasRelatedWork W4366320140 @default.
- W2964615009 hasRelatedWork W4379662533 @default.
- W2964615009 isParatext "false" @default.
- W2964615009 isRetracted "false" @default.
- W2964615009 magId "2964615009" @default.
- W2964615009 workType "article" @default.