Matches in SemOpenAlex for { <https://semopenalex.org/work/W3185339362> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3185339362 abstract "In most of the transfer learning approaches to reinforcement learning (RL) the distribution over the tasks is assumed to be stationary. Therefore, the target and source tasks are i.i.d. samples of the same distribution. Unfortunately, this assumption rarely holds in real-world conditions, e.g., due to seasonality or periodicity, evolution in the environment or faults in the sensors/actuators. In the context of this work, we consider the problem of transferring value functions through a variational method when the distribution that generates the tasks is time-variant, proposing a solution that leverages this temporal structure inherent in the task generating process. Furthermore, by means of a finite-sample analysis, the previously mentioned solution is theoretically compared to its time-invariant version. Finally, the experimental evaluation of the proposed technique is carried out on the lake Como water system representing a real-world scenario and on three different RL environments with three distinct temporal dynamics." @default.
- W3185339362 created "2021-08-02" @default.
- W3185339362 creator A5003180662 @default.
- W3185339362 creator A5017130830 @default.
- W3185339362 creator A5035547226 @default.
- W3185339362 creator A5068505840 @default.
- W3185339362 creator A5088803594 @default.
- W3185339362 creator A5091606728 @default.
- W3185339362 date "2021-07-27" @default.
- W3185339362 modified "2023-09-26" @default.
- W3185339362 title "Time-Variant Variational Transfer for Value Functions" @default.
- W3185339362 hasPublicationYear "2021" @default.
- W3185339362 type Work @default.
- W3185339362 sameAs 3185339362 @default.
- W3185339362 citedByCount "0" @default.
- W3185339362 crossrefType "proceedings-article" @default.
- W3185339362 hasAuthorship W3185339362A5003180662 @default.
- W3185339362 hasAuthorship W3185339362A5017130830 @default.
- W3185339362 hasAuthorship W3185339362A5035547226 @default.
- W3185339362 hasAuthorship W3185339362A5068505840 @default.
- W3185339362 hasAuthorship W3185339362A5088803594 @default.
- W3185339362 hasAuthorship W3185339362A5091606728 @default.
- W3185339362 hasConcept C111919701 @default.
- W3185339362 hasConcept C119599485 @default.
- W3185339362 hasConcept C126255220 @default.
- W3185339362 hasConcept C127413603 @default.
- W3185339362 hasConcept C150899416 @default.
- W3185339362 hasConcept C151730666 @default.
- W3185339362 hasConcept C154945302 @default.
- W3185339362 hasConcept C172707124 @default.
- W3185339362 hasConcept C190470478 @default.
- W3185339362 hasConcept C201995342 @default.
- W3185339362 hasConcept C2779343474 @default.
- W3185339362 hasConcept C2780451532 @default.
- W3185339362 hasConcept C33923547 @default.
- W3185339362 hasConcept C37914503 @default.
- W3185339362 hasConcept C41008148 @default.
- W3185339362 hasConcept C81299745 @default.
- W3185339362 hasConcept C86803240 @default.
- W3185339362 hasConcept C97541855 @default.
- W3185339362 hasConcept C98045186 @default.
- W3185339362 hasConceptScore W3185339362C111919701 @default.
- W3185339362 hasConceptScore W3185339362C119599485 @default.
- W3185339362 hasConceptScore W3185339362C126255220 @default.
- W3185339362 hasConceptScore W3185339362C127413603 @default.
- W3185339362 hasConceptScore W3185339362C150899416 @default.
- W3185339362 hasConceptScore W3185339362C151730666 @default.
- W3185339362 hasConceptScore W3185339362C154945302 @default.
- W3185339362 hasConceptScore W3185339362C172707124 @default.
- W3185339362 hasConceptScore W3185339362C190470478 @default.
- W3185339362 hasConceptScore W3185339362C201995342 @default.
- W3185339362 hasConceptScore W3185339362C2779343474 @default.
- W3185339362 hasConceptScore W3185339362C2780451532 @default.
- W3185339362 hasConceptScore W3185339362C33923547 @default.
- W3185339362 hasConceptScore W3185339362C37914503 @default.
- W3185339362 hasConceptScore W3185339362C41008148 @default.
- W3185339362 hasConceptScore W3185339362C81299745 @default.
- W3185339362 hasConceptScore W3185339362C86803240 @default.
- W3185339362 hasConceptScore W3185339362C97541855 @default.
- W3185339362 hasConceptScore W3185339362C98045186 @default.
- W3185339362 hasLocation W31853393621 @default.
- W3185339362 hasOpenAccess W3185339362 @default.
- W3185339362 hasPrimaryLocation W31853393621 @default.
- W3185339362 hasRelatedWork W163527819 @default.
- W3185339362 hasRelatedWork W2365327584 @default.
- W3185339362 hasRelatedWork W2462105536 @default.
- W3185339362 hasRelatedWork W25009767 @default.
- W3185339362 hasRelatedWork W2739287179 @default.
- W3185339362 hasRelatedWork W2897471074 @default.
- W3185339362 hasRelatedWork W2925005717 @default.
- W3185339362 hasRelatedWork W2950615280 @default.
- W3185339362 hasRelatedWork W2958769143 @default.
- W3185339362 hasRelatedWork W2968113041 @default.
- W3185339362 hasRelatedWork W3003632398 @default.
- W3185339362 hasRelatedWork W3029635095 @default.
- W3185339362 hasRelatedWork W3032954808 @default.
- W3185339362 hasRelatedWork W3033739625 @default.
- W3185339362 hasRelatedWork W3035154336 @default.
- W3185339362 hasRelatedWork W3036320002 @default.
- W3185339362 hasRelatedWork W3094271335 @default.
- W3185339362 hasRelatedWork W3115855231 @default.
- W3185339362 hasRelatedWork W3119417012 @default.
- W3185339362 hasRelatedWork W785831587 @default.
- W3185339362 isParatext "false" @default.
- W3185339362 isRetracted "false" @default.
- W3185339362 magId "3185339362" @default.
- W3185339362 workType "article" @default.