Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312901059> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W4312901059 abstract "This paper presents a method for learning logical task specifications and cost functions from demonstrations. Constructing specifications by hand is challenging for complex objectives and constraints in autonomous systems. Instead, we consider demonstrated task executions, whose logic structure and transition costs need to be inferred by an autonomous agent. We employ a spectral learning approach to extract a weighted finite automaton (WFA), approximating the unknown task logic. Thereafter, we define a product between the WFA for high-level task guidance and a labeled Markov decision process for low-level control. An inverse reinforcement learning (IRL) problem is considered to learn a cost function by backpropagating the loss between agent and expert behaviors through the planning algorithm. Our proposed model, termed WFA-IRL, is capable of generalizing the execution of the inferred task specification in a suite of MiniGrid environments." @default.
- W4312901059 created "2023-01-05" @default.
- W4312901059 creator A5062542913 @default.
- W4312901059 creator A5066400889 @default.
- W4312901059 date "2022-10-23" @default.
- W4312901059 modified "2023-10-16" @default.
- W4312901059 title "WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata" @default.
- W4312901059 cites W1643571618 @default.
- W4312901059 cites W1943821960 @default.
- W4312901059 cites W1970269621 @default.
- W4312901059 cites W1971086298 @default.
- W4312901059 cites W2071797744 @default.
- W4312901059 cites W2109910161 @default.
- W4312901059 cites W2134312936 @default.
- W4312901059 cites W2151958719 @default.
- W4312901059 cites W2163941698 @default.
- W4312901059 cites W2169498096 @default.
- W4312901059 cites W2169528473 @default.
- W4312901059 cites W2235884325 @default.
- W4312901059 cites W2242407529 @default.
- W4312901059 cites W2802897770 @default.
- W4312901059 cites W2883140436 @default.
- W4312901059 cites W2962951365 @default.
- W4312901059 cites W2964227312 @default.
- W4312901059 cites W2990750410 @default.
- W4312901059 cites W3038945966 @default.
- W4312901059 cites W3091379283 @default.
- W4312901059 cites W3101648496 @default.
- W4312901059 cites W3120742815 @default.
- W4312901059 doi "https://doi.org/10.1109/iros47612.2022.9981874" @default.
- W4312901059 hasPublicationYear "2022" @default.
- W4312901059 type Work @default.
- W4312901059 citedByCount "0" @default.
- W4312901059 crossrefType "proceedings-article" @default.
- W4312901059 hasAuthorship W4312901059A5062542913 @default.
- W4312901059 hasAuthorship W4312901059A5066400889 @default.
- W4312901059 hasBestOaLocation W43129010592 @default.
- W4312901059 hasConcept C105795698 @default.
- W4312901059 hasConcept C106189395 @default.
- W4312901059 hasConcept C112505250 @default.
- W4312901059 hasConcept C11413529 @default.
- W4312901059 hasConcept C119857082 @default.
- W4312901059 hasConcept C14036430 @default.
- W4312901059 hasConcept C154945302 @default.
- W4312901059 hasConcept C159886148 @default.
- W4312901059 hasConcept C162324750 @default.
- W4312901059 hasConcept C166957645 @default.
- W4312901059 hasConcept C167822520 @default.
- W4312901059 hasConcept C187736073 @default.
- W4312901059 hasConcept C199360897 @default.
- W4312901059 hasConcept C2780451532 @default.
- W4312901059 hasConcept C33923547 @default.
- W4312901059 hasConcept C41008148 @default.
- W4312901059 hasConcept C78458016 @default.
- W4312901059 hasConcept C79581498 @default.
- W4312901059 hasConcept C86803240 @default.
- W4312901059 hasConcept C95457728 @default.
- W4312901059 hasConcept C97541855 @default.
- W4312901059 hasConcept C98045186 @default.
- W4312901059 hasConceptScore W4312901059C105795698 @default.
- W4312901059 hasConceptScore W4312901059C106189395 @default.
- W4312901059 hasConceptScore W4312901059C112505250 @default.
- W4312901059 hasConceptScore W4312901059C11413529 @default.
- W4312901059 hasConceptScore W4312901059C119857082 @default.
- W4312901059 hasConceptScore W4312901059C14036430 @default.
- W4312901059 hasConceptScore W4312901059C154945302 @default.
- W4312901059 hasConceptScore W4312901059C159886148 @default.
- W4312901059 hasConceptScore W4312901059C162324750 @default.
- W4312901059 hasConceptScore W4312901059C166957645 @default.
- W4312901059 hasConceptScore W4312901059C167822520 @default.
- W4312901059 hasConceptScore W4312901059C187736073 @default.
- W4312901059 hasConceptScore W4312901059C199360897 @default.
- W4312901059 hasConceptScore W4312901059C2780451532 @default.
- W4312901059 hasConceptScore W4312901059C33923547 @default.
- W4312901059 hasConceptScore W4312901059C41008148 @default.
- W4312901059 hasConceptScore W4312901059C78458016 @default.
- W4312901059 hasConceptScore W4312901059C79581498 @default.
- W4312901059 hasConceptScore W4312901059C86803240 @default.
- W4312901059 hasConceptScore W4312901059C95457728 @default.
- W4312901059 hasConceptScore W4312901059C97541855 @default.
- W4312901059 hasConceptScore W4312901059C98045186 @default.
- W4312901059 hasFunder F4320337345 @default.
- W4312901059 hasLocation W43129010591 @default.
- W4312901059 hasLocation W43129010592 @default.
- W4312901059 hasOpenAccess W4312901059 @default.
- W4312901059 hasPrimaryLocation W43129010591 @default.
- W4312901059 hasRelatedWork W1545451257 @default.
- W4312901059 hasRelatedWork W1556532828 @default.
- W4312901059 hasRelatedWork W1574991376 @default.
- W4312901059 hasRelatedWork W1985560493 @default.
- W4312901059 hasRelatedWork W1991138660 @default.
- W4312901059 hasRelatedWork W2937181779 @default.
- W4312901059 hasRelatedWork W2949964922 @default.
- W4312901059 hasRelatedWork W3198564127 @default.
- W4312901059 hasRelatedWork W4287824211 @default.
- W4312901059 hasRelatedWork W4319083788 @default.
- W4312901059 isParatext "false" @default.
- W4312901059 isRetracted "false" @default.
- W4312901059 workType "article" @default.