Matches in SemOpenAlex for { <https://semopenalex.org/work/W2805244804> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2805244804 abstract "Common approaches to learn complex tasks in reinforcement learning include reward shaping, environmental hints, or a curriculum. Yet few studies examine how they compare to each other, when one might prefer one approach, or how they may complement each other. As a first step in this direction, we compare reward shaping, hints, and curricula for a Deep RL agent in the game of Minecraft. We seek to answer whether reward shaping, visual hints, or the curricula have the most impact on performance, which we measure as the time to reach the target, the distance from the target, the cumulative reward, or the number of actions taken. Our analyses show that performance is most impacted by the curriculum used and visual hints; shaping had less impact. For similar navigation tasks, the results suggest that designing an effective curriculum and providing appropriate hints most improve the performance. Common approaches to learn complex tasks in reinforcement learning include reward shaping, environmental hints, or a curriculum, yet few studies examine how they compare to each other. We compare these approaches for a Deep RL agent in the game of Minecraft and show performance is most impacted by the curriculum used and visual hints; shaping had less impact. For similar navigation tasks, this suggests that designing an effective curriculum with hints most improve the performance." @default.
- W2805244804 created "2018-06-13" @default.
- W2805244804 creator A5001340547 @default.
- W2805244804 creator A5044375596 @default.
- W2805244804 creator A5063634505 @default.
- W2805244804 creator A5063806691 @default.
- W2805244804 date "2018-04-29" @default.
- W2805244804 modified "2023-09-25" @default.
- W2805244804 title "Comparing Reward Shaping, Visual Hints, and Curriculum Learning" @default.
- W2805244804 doi "https://doi.org/10.1609/aaai.v32i1.12160" @default.
- W2805244804 hasPublicationYear "2018" @default.
- W2805244804 type Work @default.
- W2805244804 sameAs 2805244804 @default.
- W2805244804 citedByCount "0" @default.
- W2805244804 crossrefType "journal-article" @default.
- W2805244804 hasAuthorship W2805244804A5001340547 @default.
- W2805244804 hasAuthorship W2805244804A5044375596 @default.
- W2805244804 hasAuthorship W2805244804A5063634505 @default.
- W2805244804 hasAuthorship W2805244804A5063806691 @default.
- W2805244804 hasBestOaLocation W28052448041 @default.
- W2805244804 hasConcept C104317684 @default.
- W2805244804 hasConcept C107457646 @default.
- W2805244804 hasConcept C112313634 @default.
- W2805244804 hasConcept C127716648 @default.
- W2805244804 hasConcept C154945302 @default.
- W2805244804 hasConcept C15744967 @default.
- W2805244804 hasConcept C180747234 @default.
- W2805244804 hasConcept C185592680 @default.
- W2805244804 hasConcept C188082640 @default.
- W2805244804 hasConcept C19417346 @default.
- W2805244804 hasConcept C41008148 @default.
- W2805244804 hasConcept C47177190 @default.
- W2805244804 hasConcept C55493867 @default.
- W2805244804 hasConcept C97541855 @default.
- W2805244804 hasConceptScore W2805244804C104317684 @default.
- W2805244804 hasConceptScore W2805244804C107457646 @default.
- W2805244804 hasConceptScore W2805244804C112313634 @default.
- W2805244804 hasConceptScore W2805244804C127716648 @default.
- W2805244804 hasConceptScore W2805244804C154945302 @default.
- W2805244804 hasConceptScore W2805244804C15744967 @default.
- W2805244804 hasConceptScore W2805244804C180747234 @default.
- W2805244804 hasConceptScore W2805244804C185592680 @default.
- W2805244804 hasConceptScore W2805244804C188082640 @default.
- W2805244804 hasConceptScore W2805244804C19417346 @default.
- W2805244804 hasConceptScore W2805244804C41008148 @default.
- W2805244804 hasConceptScore W2805244804C47177190 @default.
- W2805244804 hasConceptScore W2805244804C55493867 @default.
- W2805244804 hasConceptScore W2805244804C97541855 @default.
- W2805244804 hasIssue "1" @default.
- W2805244804 hasLocation W28052448041 @default.
- W2805244804 hasOpenAccess W2805244804 @default.
- W2805244804 hasPrimaryLocation W28052448041 @default.
- W2805244804 hasRelatedWork W260766989 @default.
- W2805244804 hasRelatedWork W2748952813 @default.
- W2805244804 hasRelatedWork W2899084033 @default.
- W2805244804 hasRelatedWork W2959276766 @default.
- W2805244804 hasRelatedWork W3074294383 @default.
- W2805244804 hasRelatedWork W3111983280 @default.
- W2805244804 hasRelatedWork W3139193008 @default.
- W2805244804 hasRelatedWork W3164468573 @default.
- W2805244804 hasRelatedWork W4206669594 @default.
- W2805244804 hasRelatedWork W4295941380 @default.
- W2805244804 hasVolume "32" @default.
- W2805244804 isParatext "false" @default.
- W2805244804 isRetracted "false" @default.
- W2805244804 magId "2805244804" @default.
- W2805244804 workType "article" @default.