FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2786110872> ?p ?o ?g. }

• W2786110872 abstract "In shared autonomy, user input is combined with semi-autonomous control to achieve a common goal. The goal is often unknown ex-ante, so prior work enables agents to infer the goal from user input and assist with the task. Such methods tend to assume some combination of knowledge of the dynamics of the environment, the user's policy given their goal, and the set of possible goals the user might target, which limits their application to real-world scenarios. We propose a deep reinforcement learning framework for model-free shared autonomy that lifts these assumptions. We use human-in-the-loop reinforcement learning with neural network function approximation to learn an end-to-end mapping from environmental observation and user input to agent action values, with task reward as the only form of supervision. This approach poses the challenge of following user commands closely enough to provide the user with real-time action feedback and thereby ensure high-quality user input, but also deviating from the user's actions when they are suboptimal. We balance these two needs by discarding actions whose values fall below some threshold, then selecting the remaining action closest to the user's input. Controlled studies with users (n = 12) and synthetic pilots playing a video game, and a pilot study with users (n = 4) flying a real quadrotor, demonstrate the ability of our algorithm to assist users with real-time control tasks in which the agent cannot directly access the user's private information through observations, but receives a reward signal and user input that both depend on the user's intent. The agent learns to assist the user without access to this private information, implicitly inferring it from the user's input. This paper is a proof of concept that illustrates the potential for deep reinforcement learning to enable flexible and practical assistive systems." @default.
• W2786110872 created "2018-02-23" @default.
• W2786110872 creator A5005997281 @default.
• W2786110872 creator A5026322200 @default.
• W2786110872 creator A5060474350 @default.
• W2786110872 date "2018-02-06" @default.
• W2786110872 modified "2023-09-27" @default.
• W2786110872 title "Shared Autonomy via Deep Reinforcement Learning" @default.
• W2786110872 cites W1581800915 @default.
• W2786110872 cites W1595483645 @default.
• W2786110872 cites W1983885373 @default.
• W2786110872 cites W1986014385 @default.
• W2786110872 cites W2061562262 @default.
• W2786110872 cites W2097234820 @default.
• W2786110872 cites W2098584016 @default.
• W2786110872 cites W2098774185 @default.
• W2786110872 cites W2122223050 @default.
• W2786110872 cites W2145339207 @default.
• W2786110872 cites W2155968351 @default.
• W2786110872 cites W2156869222 @default.
• W2786110872 cites W2264407643 @default.
• W2786110872 cites W2294422333 @default.
• W2786110872 cites W2410540304 @default.
• W2786110872 cites W2527925052 @default.
• W2786110872 cites W2588104504 @default.
• W2786110872 cites W2734800126 @default.
• W2786110872 cites W2754794180 @default.
• W2786110872 cites W2760057500 @default.
• W2786110872 cites W2761873684 @default.
• W2786110872 cites W2962938178 @default.
• W2786110872 cites W3105843127 @default.
• W2786110872 hasPublicationYear "2018" @default.
• W2786110872 type Work @default.
• W2786110872 sameAs 2786110872 @default.
• W2786110872 citedByCount "27" @default.
• W2786110872 countsByYear W27861108722018 @default.
• W2786110872 countsByYear W27861108722019 @default.
• W2786110872 countsByYear W27861108722020 @default.
• W2786110872 countsByYear W27861108722021 @default.
• W2786110872 countsByYear W27861108722022 @default.
• W2786110872 crossrefType "posted-content" @default.
• W2786110872 hasAuthorship W2786110872A5005997281 @default.
• W2786110872 hasAuthorship W2786110872A5026322200 @default.
• W2786110872 hasAuthorship W2786110872A5060474350 @default.
• W2786110872 hasConcept C107457646 @default.
• W2786110872 hasConcept C111919701 @default.
• W2786110872 hasConcept C121332964 @default.
• W2786110872 hasConcept C127413603 @default.
• W2786110872 hasConcept C14036430 @default.
• W2786110872 hasConcept C154945302 @default.
• W2786110872 hasConcept C177264268 @default.
• W2786110872 hasConcept C17744445 @default.
• W2786110872 hasConcept C199360897 @default.
• W2786110872 hasConcept C199539241 @default.
• W2786110872 hasConcept C201995342 @default.
• W2786110872 hasConcept C203479927 @default.
• W2786110872 hasConcept C2775924081 @default.
• W2786110872 hasConcept C2780451532 @default.
• W2786110872 hasConcept C2780791683 @default.
• W2786110872 hasConcept C41008148 @default.
• W2786110872 hasConcept C62520636 @default.
• W2786110872 hasConcept C65414064 @default.
• W2786110872 hasConcept C6557445 @default.
• W2786110872 hasConcept C67712803 @default.
• W2786110872 hasConcept C78458016 @default.
• W2786110872 hasConcept C86803240 @default.
• W2786110872 hasConcept C89505385 @default.
• W2786110872 hasConcept C97541855 @default.
• W2786110872 hasConceptScore W2786110872C107457646 @default.
• W2786110872 hasConceptScore W2786110872C111919701 @default.
• W2786110872 hasConceptScore W2786110872C121332964 @default.
• W2786110872 hasConceptScore W2786110872C127413603 @default.
• W2786110872 hasConceptScore W2786110872C14036430 @default.
• W2786110872 hasConceptScore W2786110872C154945302 @default.
• W2786110872 hasConceptScore W2786110872C177264268 @default.
• W2786110872 hasConceptScore W2786110872C17744445 @default.
• W2786110872 hasConceptScore W2786110872C199360897 @default.
• W2786110872 hasConceptScore W2786110872C199539241 @default.
• W2786110872 hasConceptScore W2786110872C201995342 @default.
• W2786110872 hasConceptScore W2786110872C203479927 @default.
• W2786110872 hasConceptScore W2786110872C2775924081 @default.
• W2786110872 hasConceptScore W2786110872C2780451532 @default.
• W2786110872 hasConceptScore W2786110872C2780791683 @default.
• W2786110872 hasConceptScore W2786110872C41008148 @default.
• W2786110872 hasConceptScore W2786110872C62520636 @default.
• W2786110872 hasConceptScore W2786110872C65414064 @default.
• W2786110872 hasConceptScore W2786110872C6557445 @default.
• W2786110872 hasConceptScore W2786110872C67712803 @default.
• W2786110872 hasConceptScore W2786110872C78458016 @default.
• W2786110872 hasConceptScore W2786110872C86803240 @default.
• W2786110872 hasConceptScore W2786110872C89505385 @default.
• W2786110872 hasConceptScore W2786110872C97541855 @default.
• W2786110872 hasLocation W27861108721 @default.
• W2786110872 hasOpenAccess W2786110872 @default.
• W2786110872 hasPrimaryLocation W27861108721 @default.
• W2786110872 hasRelatedWork W161119602 @default.
• W2786110872 hasRelatedWork W2061562262 @default.
• W2786110872 hasRelatedWork W2098774185 @default.
• W2786110872 hasRelatedWork W2105925198 @default.
• W2786110872 hasRelatedWork W2111340349 @default.

• next