Matches in SemOpenAlex for { <https://semopenalex.org/work/W2983670306> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2983670306 abstract "We introduce an end-to-end reinforcement learning (RL) solution for the problem of sending personalized digital health interventions. Previous work has shown that personalized interventions can be obtained through RL using simple, discrete state information such as the recent activity performed. In reality however, such features are often not observed, but instead could be inferred from noisy, low-level sensor information obtained from mobile devices (e.g. accelerometers in mobile phones). One could first transform such raw data into discrete activities, but that could throw away important details and would require training a classifier to infer these discrete activities which would need a labeled training set. Instead, we propose to directly learn intervention strategies for the low-level sensor data end-to-end using deep neural networks and RL. We test our novel approach in a self-developed simulation environment which models, and generates, realistic sensor data for daily human activities and show the short-and long-term efficacy of sending personalized physical workout interventions using RL policies. We compare several different input representations and show that learning using raw sensor data is nearly as effective and much more flexible. CCS CONCEPTS • Computing methodologies → Reinforcement learning; Sequential decision making; Online learning settings;" @default.
- W2983670306 created "2019-11-22" @default.
- W2983670306 creator A5003816217 @default.
- W2983670306 creator A5007799644 @default.
- W2983670306 creator A5044217809 @default.
- W2983670306 creator A5074492402 @default.
- W2983670306 creator A5090948866 @default.
- W2983670306 date "2019-10-14" @default.
- W2983670306 modified "2023-10-14" @default.
- W2983670306 title "End-to-end Personalization of Digital Health Interventions using Raw Sensor Data with Deep Reinforcement Learning" @default.
- W2983670306 cites W2064675550 @default.
- W2983670306 cites W2076063813 @default.
- W2983670306 cites W2101786389 @default.
- W2983670306 cites W2724146920 @default.
- W2983670306 cites W2796868086 @default.
- W2983670306 cites W2811244731 @default.
- W2983670306 cites W2897297956 @default.
- W2983670306 cites W2897737265 @default.
- W2983670306 cites W2913695048 @default.
- W2983670306 cites W4236885347 @default.
- W2983670306 doi "https://doi.org/10.1145/3350546.3352527" @default.
- W2983670306 hasPublicationYear "2019" @default.
- W2983670306 type Work @default.
- W2983670306 sameAs 2983670306 @default.
- W2983670306 citedByCount "5" @default.
- W2983670306 countsByYear W29836703062018 @default.
- W2983670306 countsByYear W29836703062020 @default.
- W2983670306 countsByYear W29836703062021 @default.
- W2983670306 countsByYear W29836703062022 @default.
- W2983670306 crossrefType "proceedings-article" @default.
- W2983670306 hasAuthorship W2983670306A5003816217 @default.
- W2983670306 hasAuthorship W2983670306A5007799644 @default.
- W2983670306 hasAuthorship W2983670306A5044217809 @default.
- W2983670306 hasAuthorship W2983670306A5074492402 @default.
- W2983670306 hasAuthorship W2983670306A5090948866 @default.
- W2983670306 hasBestOaLocation W29836703062 @default.
- W2983670306 hasConcept C107457646 @default.
- W2983670306 hasConcept C127413603 @default.
- W2983670306 hasConcept C132964779 @default.
- W2983670306 hasConcept C136764020 @default.
- W2983670306 hasConcept C154945302 @default.
- W2983670306 hasConcept C159110408 @default.
- W2983670306 hasConcept C183003079 @default.
- W2983670306 hasConcept C199360897 @default.
- W2983670306 hasConcept C27415008 @default.
- W2983670306 hasConcept C41008148 @default.
- W2983670306 hasConcept C66938386 @default.
- W2983670306 hasConcept C67203356 @default.
- W2983670306 hasConcept C71924100 @default.
- W2983670306 hasConcept C97541855 @default.
- W2983670306 hasConceptScore W2983670306C107457646 @default.
- W2983670306 hasConceptScore W2983670306C127413603 @default.
- W2983670306 hasConceptScore W2983670306C132964779 @default.
- W2983670306 hasConceptScore W2983670306C136764020 @default.
- W2983670306 hasConceptScore W2983670306C154945302 @default.
- W2983670306 hasConceptScore W2983670306C159110408 @default.
- W2983670306 hasConceptScore W2983670306C183003079 @default.
- W2983670306 hasConceptScore W2983670306C199360897 @default.
- W2983670306 hasConceptScore W2983670306C27415008 @default.
- W2983670306 hasConceptScore W2983670306C41008148 @default.
- W2983670306 hasConceptScore W2983670306C66938386 @default.
- W2983670306 hasConceptScore W2983670306C67203356 @default.
- W2983670306 hasConceptScore W2983670306C71924100 @default.
- W2983670306 hasConceptScore W2983670306C97541855 @default.
- W2983670306 hasLocation W29836703061 @default.
- W2983670306 hasLocation W29836703062 @default.
- W2983670306 hasOpenAccess W2983670306 @default.
- W2983670306 hasPrimaryLocation W29836703061 @default.
- W2983670306 hasRelatedWork W2108595774 @default.
- W2983670306 hasRelatedWork W2336151140 @default.
- W2983670306 hasRelatedWork W2923653485 @default.
- W2983670306 hasRelatedWork W2952472710 @default.
- W2983670306 hasRelatedWork W2957776456 @default.
- W2983670306 hasRelatedWork W4206266697 @default.
- W2983670306 hasRelatedWork W4224287422 @default.
- W2983670306 hasRelatedWork W4255994452 @default.
- W2983670306 hasRelatedWork W4319773215 @default.
- W2983670306 hasRelatedWork W4361026739 @default.
- W2983670306 isParatext "false" @default.
- W2983670306 isRetracted "false" @default.
- W2983670306 magId "2983670306" @default.
- W2983670306 workType "article" @default.