Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893600742> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2893600742 abstract "Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the future. In this paper a curiosity-driven agent is extended to use these predictions directly for training. To achieve this, the agent predicts the value function of the next state at any point in time. Subsequently, the consistency of this prediction with the current value function is measured, which is then used as a regularization term in the loss function of the algorithm. Experiments were made on grid-world environments as well as on a 3D navigation task, both with sparse rewards. In the first case the extended agent is able to learn significantly faster than the baselines." @default.
- W2893600742 created "2018-10-05" @default.
- W2893600742 creator A5012797145 @default.
- W2893600742 creator A5036362995 @default.
- W2893600742 creator A5047790045 @default.
- W2893600742 creator A5078339613 @default.
- W2893600742 date "2018-11-01" @default.
- W2893600742 modified "2023-09-23" @default.
- W2893600742 title "Using State Predictions for Value Regularization in Curiosity Driven Deep Reinforcement Learning" @default.
- W2893600742 doi "https://doi.org/10.1109/ictai.2018.00015" @default.
- W2893600742 hasPublicationYear "2018" @default.
- W2893600742 type Work @default.
- W2893600742 sameAs 2893600742 @default.
- W2893600742 citedByCount "3" @default.
- W2893600742 countsByYear W28936007422019 @default.
- W2893600742 countsByYear W28936007422020 @default.
- W2893600742 countsByYear W28936007422021 @default.
- W2893600742 crossrefType "proceedings-article" @default.
- W2893600742 hasAuthorship W2893600742A5012797145 @default.
- W2893600742 hasAuthorship W2893600742A5036362995 @default.
- W2893600742 hasAuthorship W2893600742A5047790045 @default.
- W2893600742 hasAuthorship W2893600742A5078339613 @default.
- W2893600742 hasBestOaLocation W28936007422 @default.
- W2893600742 hasConcept C119857082 @default.
- W2893600742 hasConcept C126255220 @default.
- W2893600742 hasConcept C127413603 @default.
- W2893600742 hasConcept C14036430 @default.
- W2893600742 hasConcept C14646407 @default.
- W2893600742 hasConcept C154945302 @default.
- W2893600742 hasConcept C15744967 @default.
- W2893600742 hasConcept C187691185 @default.
- W2893600742 hasConcept C201995342 @default.
- W2893600742 hasConcept C2524010 @default.
- W2893600742 hasConcept C2776135515 @default.
- W2893600742 hasConcept C2776436953 @default.
- W2893600742 hasConcept C2780451532 @default.
- W2893600742 hasConcept C33435437 @default.
- W2893600742 hasConcept C33923547 @default.
- W2893600742 hasConcept C41008148 @default.
- W2893600742 hasConcept C77805123 @default.
- W2893600742 hasConcept C78458016 @default.
- W2893600742 hasConcept C86803240 @default.
- W2893600742 hasConcept C97541855 @default.
- W2893600742 hasConceptScore W2893600742C119857082 @default.
- W2893600742 hasConceptScore W2893600742C126255220 @default.
- W2893600742 hasConceptScore W2893600742C127413603 @default.
- W2893600742 hasConceptScore W2893600742C14036430 @default.
- W2893600742 hasConceptScore W2893600742C14646407 @default.
- W2893600742 hasConceptScore W2893600742C154945302 @default.
- W2893600742 hasConceptScore W2893600742C15744967 @default.
- W2893600742 hasConceptScore W2893600742C187691185 @default.
- W2893600742 hasConceptScore W2893600742C201995342 @default.
- W2893600742 hasConceptScore W2893600742C2524010 @default.
- W2893600742 hasConceptScore W2893600742C2776135515 @default.
- W2893600742 hasConceptScore W2893600742C2776436953 @default.
- W2893600742 hasConceptScore W2893600742C2780451532 @default.
- W2893600742 hasConceptScore W2893600742C33435437 @default.
- W2893600742 hasConceptScore W2893600742C33923547 @default.
- W2893600742 hasConceptScore W2893600742C41008148 @default.
- W2893600742 hasConceptScore W2893600742C77805123 @default.
- W2893600742 hasConceptScore W2893600742C78458016 @default.
- W2893600742 hasConceptScore W2893600742C86803240 @default.
- W2893600742 hasConceptScore W2893600742C97541855 @default.
- W2893600742 hasLocation W28936007421 @default.
- W2893600742 hasLocation W28936007422 @default.
- W2893600742 hasOpenAccess W2893600742 @default.
- W2893600742 hasPrimaryLocation W28936007421 @default.
- W2893600742 hasRelatedWork W1559336379 @default.
- W2893600742 hasRelatedWork W2109590452 @default.
- W2893600742 hasRelatedWork W2129015292 @default.
- W2893600742 hasRelatedWork W2734912394 @default.
- W2893600742 hasRelatedWork W2893600742 @default.
- W2893600742 hasRelatedWork W2918392679 @default.
- W2893600742 hasRelatedWork W2950240244 @default.
- W2893600742 hasRelatedWork W3011591403 @default.
- W2893600742 hasRelatedWork W3132645524 @default.
- W2893600742 hasRelatedWork W4286894536 @default.
- W2893600742 isParatext "false" @default.
- W2893600742 isRetracted "false" @default.
- W2893600742 magId "2893600742" @default.
- W2893600742 workType "article" @default.