Matches in SemOpenAlex for { <https://semopenalex.org/work/W3167527548> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3167527548 endingPage "2958" @default.
- W3167527548 startingPage "2948" @default.
- W3167527548 abstract "Reinforcement learning (RL) has made a lot of advances for solving a single problem in a given environment; but learning policies that generalize to unseen variations of a problem remains challenging. To improve sample efficiency for learning on such instances of a problem domain, we present Self-Paced Context Evaluation (SPaCE). Based on self-paced learning, spc automatically generates task curricula online with little computational overhead. To this end, SPaCE leverages information contained in state values during training to accelerate and improve training performance as well as generalization capabilities to new instances from the same problem domain. Nevertheless, SPaCE is independent of the problem domain at hand and can be applied on top of any RL agent with state-value function approximation. We demonstrate SPaCE's ability to speed up learning of different value-based RL agents on two environments, showing better generalization capabilities and up to 10x faster learning compared to naive approaches such as round robin or SPDRL, as the closest state-of-the-art approach." @default.
- W3167527548 created "2021-06-22" @default.
- W3167527548 creator A5031002895 @default.
- W3167527548 creator A5038833033 @default.
- W3167527548 creator A5045511267 @default.
- W3167527548 creator A5059374472 @default.
- W3167527548 date "2021-07-18" @default.
- W3167527548 modified "2023-09-23" @default.
- W3167527548 title "Self-Paced Context Evaluation for Contextual Reinforcement Learning" @default.
- W3167527548 hasPublicationYear "2021" @default.
- W3167527548 type Work @default.
- W3167527548 sameAs 3167527548 @default.
- W3167527548 citedByCount "1" @default.
- W3167527548 countsByYear W31675275482021 @default.
- W3167527548 crossrefType "proceedings-article" @default.
- W3167527548 hasAuthorship W3167527548A5031002895 @default.
- W3167527548 hasAuthorship W3167527548A5038833033 @default.
- W3167527548 hasAuthorship W3167527548A5045511267 @default.
- W3167527548 hasAuthorship W3167527548A5059374472 @default.
- W3167527548 hasConcept C105795698 @default.
- W3167527548 hasConcept C111919701 @default.
- W3167527548 hasConcept C119857082 @default.
- W3167527548 hasConcept C126255220 @default.
- W3167527548 hasConcept C134306372 @default.
- W3167527548 hasConcept C14036430 @default.
- W3167527548 hasConcept C14646407 @default.
- W3167527548 hasConcept C151730666 @default.
- W3167527548 hasConcept C154945302 @default.
- W3167527548 hasConcept C162324750 @default.
- W3167527548 hasConcept C177148314 @default.
- W3167527548 hasConcept C187736073 @default.
- W3167527548 hasConcept C2778572836 @default.
- W3167527548 hasConcept C2779343474 @default.
- W3167527548 hasConcept C2779960059 @default.
- W3167527548 hasConcept C2780451532 @default.
- W3167527548 hasConcept C33923547 @default.
- W3167527548 hasConcept C36503486 @default.
- W3167527548 hasConcept C41008148 @default.
- W3167527548 hasConcept C72434380 @default.
- W3167527548 hasConcept C78458016 @default.
- W3167527548 hasConcept C86803240 @default.
- W3167527548 hasConcept C97541855 @default.
- W3167527548 hasConceptScore W3167527548C105795698 @default.
- W3167527548 hasConceptScore W3167527548C111919701 @default.
- W3167527548 hasConceptScore W3167527548C119857082 @default.
- W3167527548 hasConceptScore W3167527548C126255220 @default.
- W3167527548 hasConceptScore W3167527548C134306372 @default.
- W3167527548 hasConceptScore W3167527548C14036430 @default.
- W3167527548 hasConceptScore W3167527548C14646407 @default.
- W3167527548 hasConceptScore W3167527548C151730666 @default.
- W3167527548 hasConceptScore W3167527548C154945302 @default.
- W3167527548 hasConceptScore W3167527548C162324750 @default.
- W3167527548 hasConceptScore W3167527548C177148314 @default.
- W3167527548 hasConceptScore W3167527548C187736073 @default.
- W3167527548 hasConceptScore W3167527548C2778572836 @default.
- W3167527548 hasConceptScore W3167527548C2779343474 @default.
- W3167527548 hasConceptScore W3167527548C2779960059 @default.
- W3167527548 hasConceptScore W3167527548C2780451532 @default.
- W3167527548 hasConceptScore W3167527548C33923547 @default.
- W3167527548 hasConceptScore W3167527548C36503486 @default.
- W3167527548 hasConceptScore W3167527548C41008148 @default.
- W3167527548 hasConceptScore W3167527548C72434380 @default.
- W3167527548 hasConceptScore W3167527548C78458016 @default.
- W3167527548 hasConceptScore W3167527548C86803240 @default.
- W3167527548 hasConceptScore W3167527548C97541855 @default.
- W3167527548 hasOpenAccess W3167527548 @default.
- W3167527548 hasRelatedWork W1526807135 @default.
- W3167527548 hasRelatedWork W2166265228 @default.
- W3167527548 hasRelatedWork W2195382509 @default.
- W3167527548 hasRelatedWork W2289410116 @default.
- W3167527548 hasRelatedWork W2466611570 @default.
- W3167527548 hasRelatedWork W2528846071 @default.
- W3167527548 hasRelatedWork W2953981431 @default.
- W3167527548 hasRelatedWork W3019379181 @default.
- W3167527548 hasRelatedWork W3029221344 @default.
- W3167527548 hasRelatedWork W3034359401 @default.
- W3167527548 hasRelatedWork W3037179286 @default.
- W3167527548 hasRelatedWork W3041557432 @default.
- W3167527548 hasRelatedWork W3045402999 @default.
- W3167527548 hasRelatedWork W3046755562 @default.
- W3167527548 hasRelatedWork W3090106354 @default.
- W3167527548 hasRelatedWork W3127235394 @default.
- W3167527548 hasRelatedWork W3131824536 @default.
- W3167527548 hasRelatedWork W3170914142 @default.
- W3167527548 hasRelatedWork W3172076556 @default.
- W3167527548 hasRelatedWork W3209208698 @default.
- W3167527548 isParatext "false" @default.
- W3167527548 isRetracted "false" @default.
- W3167527548 magId "3167527548" @default.
- W3167527548 workType "article" @default.