Matches in SemOpenAlex for { <https://semopenalex.org/work/W4323706305> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4323706305 abstract "Reinforcement learning (RL) presents numerous benefits compared to rule-based approaches in various applications. Privacy concerns have grown with the widespread use of RL trained with privacy-sensitive data in IoT devices, especially for human-in-the-loop systems. On the one hand, RL methods enhance the user experience by trying to adapt to the highly dynamic nature of humans. On the other hand, trained policies can leak the user's private information. Recent attention has been drawn to designing privacy-aware RL algorithms while maintaining an acceptable system utility. A central challenge in designing privacy-aware RL, especially for human-in-the-loop systems, is that humans have intrinsic variability and their preferences and behavior evolve. The effect of one privacy leak mitigation can be different for the same human or across different humans over time. Hence, we can not design one fixed model for privacy-aware RL that fits all. To that end, we propose adaPARL, an adaptive approach for privacy-aware RL, especially for human-in-the-loop IoT systems. adaPARL provides a personalized privacy-utility trade-off depending on human behavior and preference. We validate the proposed adaPARL on two IoT applications, namely (i) Human-in-the-Loop Smart Home and (ii) Human-in-the-Loop Virtual Reality (VR) Smart Classroom. Results obtained on these two applications validate the generality of adaPARL and its ability to provide a personalized privacy-utility trade-off. On average, for the first application, adaPARL improves the utility by $57%$ over the baseline and by $43%$ over randomization. adaPARL also reduces the privacy leak by $23%$ on average. For the second application, adaPARL decreases the privacy leak to $44%$ before the utility drops by $15%$." @default.
- W4323706305 created "2023-03-10" @default.
- W4323706305 creator A5007697058 @default.
- W4323706305 creator A5015005773 @default.
- W4323706305 creator A5038820344 @default.
- W4323706305 date "2023-05-09" @default.
- W4323706305 modified "2023-09-26" @default.
- W4323706305 title "adaPARL: Adaptive Privacy-Aware Reinforcement Learning for Sequential Decision Making Human-in-the-Loop Systems" @default.
- W4323706305 cites W2075270873 @default.
- W4323706305 cites W2084553975 @default.
- W4323706305 cites W2092850413 @default.
- W4323706305 cites W2115003018 @default.
- W4323706305 cites W2115873741 @default.
- W4323706305 cites W2140436732 @default.
- W4323706305 cites W2603580142 @default.
- W4323706305 cites W2735318784 @default.
- W4323706305 cites W2796665034 @default.
- W4323706305 cites W2800151429 @default.
- W4323706305 cites W2898091853 @default.
- W4323706305 cites W2972592048 @default.
- W4323706305 cites W3011865677 @default.
- W4323706305 cites W3011880926 @default.
- W4323706305 cites W3027451243 @default.
- W4323706305 cites W3032407425 @default.
- W4323706305 cites W3046584951 @default.
- W4323706305 cites W3086540722 @default.
- W4323706305 cites W3161302686 @default.
- W4323706305 cites W3162495614 @default.
- W4323706305 cites W4213341067 @default.
- W4323706305 cites W4283318546 @default.
- W4323706305 doi "https://doi.org/10.1145/3576842.3582325" @default.
- W4323706305 hasPublicationYear "2023" @default.
- W4323706305 type Work @default.
- W4323706305 citedByCount "0" @default.
- W4323706305 crossrefType "proceedings-article" @default.
- W4323706305 hasAuthorship W4323706305A5007697058 @default.
- W4323706305 hasAuthorship W4323706305A5015005773 @default.
- W4323706305 hasAuthorship W4323706305A5038820344 @default.
- W4323706305 hasBestOaLocation W43237063051 @default.
- W4323706305 hasConcept C107457646 @default.
- W4323706305 hasConcept C119857082 @default.
- W4323706305 hasConcept C123201435 @default.
- W4323706305 hasConcept C154945302 @default.
- W4323706305 hasConcept C15744967 @default.
- W4323706305 hasConcept C2780626000 @default.
- W4323706305 hasConcept C2780767217 @default.
- W4323706305 hasConcept C38652104 @default.
- W4323706305 hasConcept C41008148 @default.
- W4323706305 hasConcept C542102704 @default.
- W4323706305 hasConcept C97541855 @default.
- W4323706305 hasConceptScore W4323706305C107457646 @default.
- W4323706305 hasConceptScore W4323706305C119857082 @default.
- W4323706305 hasConceptScore W4323706305C123201435 @default.
- W4323706305 hasConceptScore W4323706305C154945302 @default.
- W4323706305 hasConceptScore W4323706305C15744967 @default.
- W4323706305 hasConceptScore W4323706305C2780626000 @default.
- W4323706305 hasConceptScore W4323706305C2780767217 @default.
- W4323706305 hasConceptScore W4323706305C38652104 @default.
- W4323706305 hasConceptScore W4323706305C41008148 @default.
- W4323706305 hasConceptScore W4323706305C542102704 @default.
- W4323706305 hasConceptScore W4323706305C97541855 @default.
- W4323706305 hasFunder F4320306076 @default.
- W4323706305 hasLocation W43237063051 @default.
- W4323706305 hasLocation W43237063052 @default.
- W4323706305 hasOpenAccess W4323706305 @default.
- W4323706305 hasPrimaryLocation W43237063051 @default.
- W4323706305 hasRelatedWork W1562959674 @default.
- W4323706305 hasRelatedWork W2803281228 @default.
- W4323706305 hasRelatedWork W2923653485 @default.
- W4323706305 hasRelatedWork W2957776456 @default.
- W4323706305 hasRelatedWork W3022038857 @default.
- W4323706305 hasRelatedWork W3088315509 @default.
- W4323706305 hasRelatedWork W4205364923 @default.
- W4323706305 hasRelatedWork W4210912933 @default.
- W4323706305 hasRelatedWork W4319083788 @default.
- W4323706305 hasRelatedWork W4323706305 @default.
- W4323706305 isParatext "false" @default.
- W4323706305 isRetracted "false" @default.
- W4323706305 workType "article" @default.