Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211259721> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W3211259721 endingPage "2242" @default.
- W3211259721 startingPage "2228" @default.
- W3211259721 abstract "Learning-from-demonstrations is an emerging paradigm to obtain effective robot control policies for complex tasks via reinforcement learning without the need to explicitly design reward functions. However, it is susceptible to imperfections in demonstrations and also raises concerns of safety and interpretability in the learned control policies. To address these issues, we use Signal Temporal Logic to evaluate and rank the quality of demonstrations. Temporal logic-based specifications allow us to create non-Markovian rewards, and also define interesting causal dependencies between tasks such as sequential task specifications. We validate our approach through experiments on discrete-world and OpenAI Gym environments, and show that our approach outperforms the state-of-the-art Maximum Causal Entropy Inverse Reinforcement Learning." @default.
- W3211259721 created "2021-11-08" @default.
- W3211259721 creator A5010006741 @default.
- W3211259721 creator A5053625971 @default.
- W3211259721 creator A5057473400 @default.
- W3211259721 date "2021-10-04" @default.
- W3211259721 modified "2023-09-26" @default.
- W3211259721 title "Learning from Demonstrations using Signal Temporal Logic" @default.
- W3211259721 hasPublicationYear "2021" @default.
- W3211259721 type Work @default.
- W3211259721 sameAs 3211259721 @default.
- W3211259721 citedByCount "1" @default.
- W3211259721 countsByYear W32112597212021 @default.
- W3211259721 crossrefType "journal-article" @default.
- W3211259721 hasAuthorship W3211259721A5010006741 @default.
- W3211259721 hasAuthorship W3211259721A5053625971 @default.
- W3211259721 hasAuthorship W3211259721A5057473400 @default.
- W3211259721 hasConcept C119857082 @default.
- W3211259721 hasConcept C127413603 @default.
- W3211259721 hasConcept C154945302 @default.
- W3211259721 hasConcept C201995342 @default.
- W3211259721 hasConcept C25016198 @default.
- W3211259721 hasConcept C2780451532 @default.
- W3211259721 hasConcept C2781067378 @default.
- W3211259721 hasConcept C41008148 @default.
- W3211259721 hasConcept C80444323 @default.
- W3211259721 hasConcept C97541855 @default.
- W3211259721 hasConceptScore W3211259721C119857082 @default.
- W3211259721 hasConceptScore W3211259721C127413603 @default.
- W3211259721 hasConceptScore W3211259721C154945302 @default.
- W3211259721 hasConceptScore W3211259721C201995342 @default.
- W3211259721 hasConceptScore W3211259721C25016198 @default.
- W3211259721 hasConceptScore W3211259721C2780451532 @default.
- W3211259721 hasConceptScore W3211259721C2781067378 @default.
- W3211259721 hasConceptScore W3211259721C41008148 @default.
- W3211259721 hasConceptScore W3211259721C80444323 @default.
- W3211259721 hasConceptScore W3211259721C97541855 @default.
- W3211259721 hasLocation W32112597211 @default.
- W3211259721 hasOpenAccess W3211259721 @default.
- W3211259721 hasPrimaryLocation W32112597211 @default.
- W3211259721 hasRelatedWork W1744884320 @default.
- W3211259721 hasRelatedWork W2402540331 @default.
- W3211259721 hasRelatedWork W2759757439 @default.
- W3211259721 hasRelatedWork W2800367501 @default.
- W3211259721 hasRelatedWork W2884389172 @default.
- W3211259721 hasRelatedWork W2951823923 @default.
- W3211259721 hasRelatedWork W2963391602 @default.
- W3211259721 hasRelatedWork W2965015991 @default.
- W3211259721 hasRelatedWork W2965600677 @default.
- W3211259721 hasRelatedWork W2974569780 @default.
- W3211259721 hasRelatedWork W2993149128 @default.
- W3211259721 hasRelatedWork W2995179464 @default.
- W3211259721 hasRelatedWork W2998509800 @default.
- W3211259721 hasRelatedWork W3092068599 @default.
- W3211259721 hasRelatedWork W3095695436 @default.
- W3211259721 hasRelatedWork W3096277050 @default.
- W3211259721 hasRelatedWork W3125547903 @default.
- W3211259721 hasRelatedWork W3130127426 @default.
- W3211259721 hasRelatedWork W3130555041 @default.
- W3211259721 hasRelatedWork W3213085571 @default.
- W3211259721 isParatext "false" @default.
- W3211259721 isRetracted "false" @default.
- W3211259721 magId "3211259721" @default.
- W3211259721 workType "article" @default.