Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893725421> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2893725421 abstract "In this paper, we show how Behavior Trees that have performance guarantees, in terms of safety and goal convergence, can be extended with components that were designed using machine learning, without destroying those performance guarantees. Machine learning approaches such as reinforcement learning or learning from demonstration can be very appealing to AI designers that want efficient and realistic behaviors in their agents. However, those algorithms seldom provide guarantees for solving the given task in all different situations while keeping the agent safe. Instead, such guarantees are often easier to find for manually designed model based approaches. In this paper we exploit the modularity of Behavior trees to extend a given design with an efficient, but possibly unreliable, machine learning component in a way that preserves the guarantees. The approach is illustrated with an inverted pendulum example." @default.
- W2893725421 created "2018-10-05" @default.
- W2893725421 creator A5019272905 @default.
- W2893725421 creator A5070754732 @default.
- W2893725421 date "2022-12-06" @default.
- W2893725421 modified "2023-10-18" @default.
- W2893725421 title "Adding Neural Network Controllers to Behavior Trees without Destroying Performance Guarantees" @default.
- W2893725421 cites W1524728167 @default.
- W2893725421 cites W1966910298 @default.
- W2893725421 cites W2007506196 @default.
- W2893725421 cites W2132714442 @default.
- W2893725421 cites W2145339207 @default.
- W2893725421 cites W2165744968 @default.
- W2893725421 cites W2257979135 @default.
- W2893725421 cites W2328646735 @default.
- W2893725421 cites W2483880798 @default.
- W2893725421 cites W2521617762 @default.
- W2893725421 cites W2550336733 @default.
- W2893725421 cites W2567075875 @default.
- W2893725421 cites W2967901646 @default.
- W2893725421 cites W3024044737 @default.
- W2893725421 cites W3082488836 @default.
- W2893725421 cites W3119289712 @default.
- W2893725421 cites W3197993875 @default.
- W2893725421 doi "https://doi.org/10.1109/cdc51059.2022.9992501" @default.
- W2893725421 hasPublicationYear "2022" @default.
- W2893725421 type Work @default.
- W2893725421 sameAs 2893725421 @default.
- W2893725421 citedByCount "6" @default.
- W2893725421 countsByYear W28937254212018 @default.
- W2893725421 countsByYear W28937254212019 @default.
- W2893725421 countsByYear W28937254212020 @default.
- W2893725421 countsByYear W28937254212021 @default.
- W2893725421 crossrefType "proceedings-article" @default.
- W2893725421 hasAuthorship W2893725421A5019272905 @default.
- W2893725421 hasAuthorship W2893725421A5070754732 @default.
- W2893725421 hasBestOaLocation W28937254212 @default.
- W2893725421 hasConcept C154945302 @default.
- W2893725421 hasConcept C2775924081 @default.
- W2893725421 hasConcept C31258907 @default.
- W2893725421 hasConcept C41008148 @default.
- W2893725421 hasConcept C47446073 @default.
- W2893725421 hasConcept C50644808 @default.
- W2893725421 hasConceptScore W2893725421C154945302 @default.
- W2893725421 hasConceptScore W2893725421C2775924081 @default.
- W2893725421 hasConceptScore W2893725421C31258907 @default.
- W2893725421 hasConceptScore W2893725421C41008148 @default.
- W2893725421 hasConceptScore W2893725421C47446073 @default.
- W2893725421 hasConceptScore W2893725421C50644808 @default.
- W2893725421 hasLocation W28937254211 @default.
- W2893725421 hasLocation W28937254212 @default.
- W2893725421 hasOpenAccess W2893725421 @default.
- W2893725421 hasPrimaryLocation W28937254211 @default.
- W2893725421 hasRelatedWork W2056939145 @default.
- W2893725421 hasRelatedWork W2130966263 @default.
- W2893725421 hasRelatedWork W2377690029 @default.
- W2893725421 hasRelatedWork W2386387936 @default.
- W2893725421 hasRelatedWork W2390279801 @default.
- W2893725421 hasRelatedWork W2748952813 @default.
- W2893725421 hasRelatedWork W2755440427 @default.
- W2893725421 hasRelatedWork W2899084033 @default.
- W2893725421 hasRelatedWork W572730611 @default.
- W2893725421 hasRelatedWork W1921873737 @default.
- W2893725421 isParatext "false" @default.
- W2893725421 isRetracted "false" @default.
- W2893725421 magId "2893725421" @default.
- W2893725421 workType "article" @default.