Matches in SemOpenAlex for { <https://semopenalex.org/work/W2909728541> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2909728541 abstract "Behavior trees (BT) are a popular control architecture in the computer game industry, and have been more recently applied in robotics. One open question is how can intelligent agents/robots autonomously acquire their behavior trees for task level control? In contrast with existing approaches that either refine an initially given BT, or directly build the BT based on human feedback/demonstration, we leverage reinforcement learning (RL) that allows robots to autonomously learn control policies by repeated task interaction, but often expressed in a language more difficult to interpret than BTs. The learned control policy is then converted to a behavior tree via our proposed <i xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>decanonicalization</i> algorithm. The feasibility of this idea is based on a proposed notion of <i xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>canonical behavior</i> trees (CBT). In particular, we show (1) CBTs are sufficiently expressive to capture RL control policies, and (2) that RL can be independent of an optimal behavior permutation, despite the BT convention of left-to-right priority, thus obviating the need for a combinatorial search. Two evaluation domains help illustrate our approach." @default.
- W2909728541 created "2019-01-25" @default.
- W2909728541 creator A5025954824 @default.
- W2909728541 date "2018-10-01" @default.
- W2909728541 modified "2023-10-01" @default.
- W2909728541 title "Autonomous Acquisition of Behavior Trees for Robot Control" @default.
- W2909728541 cites W1642239575 @default.
- W2909728541 cites W1699699942 @default.
- W2909728541 cites W1963549352 @default.
- W2909728541 cites W1994005705 @default.
- W2909728541 cites W2007506196 @default.
- W2909728541 cites W2075644540 @default.
- W2909728541 cites W2097856935 @default.
- W2909728541 cites W2105761964 @default.
- W2909728541 cites W2109910161 @default.
- W2909728541 cites W2171246729 @default.
- W2909728541 cites W2292533394 @default.
- W2909728541 cites W4214717370 @default.
- W2909728541 cites W4244883386 @default.
- W2909728541 doi "https://doi.org/10.1109/iros.2018.8594083" @default.
- W2909728541 hasPublicationYear "2018" @default.
- W2909728541 type Work @default.
- W2909728541 sameAs 2909728541 @default.
- W2909728541 citedByCount "25" @default.
- W2909728541 countsByYear W29097285412019 @default.
- W2909728541 countsByYear W29097285412020 @default.
- W2909728541 countsByYear W29097285412021 @default.
- W2909728541 countsByYear W29097285412022 @default.
- W2909728541 countsByYear W29097285412023 @default.
- W2909728541 crossrefType "proceedings-article" @default.
- W2909728541 hasAuthorship W2909728541A5025954824 @default.
- W2909728541 hasConcept C111919701 @default.
- W2909728541 hasConcept C113174947 @default.
- W2909728541 hasConcept C119857082 @default.
- W2909728541 hasConcept C134306372 @default.
- W2909728541 hasConcept C153083717 @default.
- W2909728541 hasConcept C154945302 @default.
- W2909728541 hasConcept C162324750 @default.
- W2909728541 hasConcept C187736073 @default.
- W2909728541 hasConcept C2775924081 @default.
- W2909728541 hasConcept C2780200862 @default.
- W2909728541 hasConcept C2780451532 @default.
- W2909728541 hasConcept C33923547 @default.
- W2909728541 hasConcept C34413123 @default.
- W2909728541 hasConcept C41008148 @default.
- W2909728541 hasConcept C90509273 @default.
- W2909728541 hasConcept C97541855 @default.
- W2909728541 hasConceptScore W2909728541C111919701 @default.
- W2909728541 hasConceptScore W2909728541C113174947 @default.
- W2909728541 hasConceptScore W2909728541C119857082 @default.
- W2909728541 hasConceptScore W2909728541C134306372 @default.
- W2909728541 hasConceptScore W2909728541C153083717 @default.
- W2909728541 hasConceptScore W2909728541C154945302 @default.
- W2909728541 hasConceptScore W2909728541C162324750 @default.
- W2909728541 hasConceptScore W2909728541C187736073 @default.
- W2909728541 hasConceptScore W2909728541C2775924081 @default.
- W2909728541 hasConceptScore W2909728541C2780200862 @default.
- W2909728541 hasConceptScore W2909728541C2780451532 @default.
- W2909728541 hasConceptScore W2909728541C33923547 @default.
- W2909728541 hasConceptScore W2909728541C34413123 @default.
- W2909728541 hasConceptScore W2909728541C41008148 @default.
- W2909728541 hasConceptScore W2909728541C90509273 @default.
- W2909728541 hasConceptScore W2909728541C97541855 @default.
- W2909728541 hasLocation W29097285411 @default.
- W2909728541 hasOpenAccess W2909728541 @default.
- W2909728541 hasPrimaryLocation W29097285411 @default.
- W2909728541 hasRelatedWork W3004582154 @default.
- W2909728541 hasRelatedWork W3036453832 @default.
- W2909728541 hasRelatedWork W3074294383 @default.
- W2909728541 hasRelatedWork W3170628611 @default.
- W2909728541 hasRelatedWork W3198608914 @default.
- W2909728541 hasRelatedWork W3204243516 @default.
- W2909728541 hasRelatedWork W3212843968 @default.
- W2909728541 hasRelatedWork W4233452137 @default.
- W2909728541 hasRelatedWork W4297949354 @default.
- W2909728541 hasRelatedWork W4319083788 @default.
- W2909728541 isParatext "false" @default.
- W2909728541 isRetracted "false" @default.
- W2909728541 magId "2909728541" @default.
- W2909728541 workType "article" @default.