Matches in SemOpenAlex for { <https://semopenalex.org/work/W2924156739> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2924156739 abstract "Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning process. Real world systems would realistically fail or break before an optimal controller can be learned. To address this issue, we propose a controller architecture that combines (1) a model-free RL-based controller with (2) model-based controllers utilizing control barrier functions (CBFs) and (3) on-line learning of the unknown system dynamics, in order to ensure safety during learning. Our general framework leverages the success of RL algorithms to learn high-performance controllers, while the CBF-based controllers both guarantee safety and guide the learning process by constraining the set of explorable polices. We utilize Gaussian Processes (GPs) to model the system dynamics and its uncertainties. Our novel controller synthesis algorithm, RL-CBF, guarantees safety with high probability during the learning process, regardless of the RL algorithm used, and demonstrates greater policy exploration efficiency. We test our algorithm on (1) control of an inverted pendulum and (2) autonomous car-following with wireless vehicle-to-vehicle communication, and show that our algorithm attains much greater sample efficiency in learning than other state-of-the-art algorithms and maintains safety during the entire learning process." @default.
- W2924156739 created "2019-04-01" @default.
- W2924156739 creator A5002930599 @default.
- W2924156739 creator A5043415749 @default.
- W2924156739 creator A5068600217 @default.
- W2924156739 creator A5089532118 @default.
- W2924156739 date "2019-03-20" @default.
- W2924156739 modified "2023-09-25" @default.
- W2924156739 title "End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks" @default.
- W2924156739 cites W1580216809 @default.
- W2924156739 cites W1845972764 @default.
- W2924156739 cites W1963790880 @default.
- W2924156739 cites W1999874108 @default.
- W2924156739 cites W2098432798 @default.
- W2924156739 cites W2130178506 @default.
- W2924156739 cites W2134122536 @default.
- W2924156739 cites W2134491302 @default.
- W2924156739 cites W2158323882 @default.
- W2924156739 cites W2164479831 @default.
- W2924156739 cites W2165150801 @default.
- W2924156739 cites W2173248099 @default.
- W2924156739 cites W2342662072 @default.
- W2924156739 cites W2586823359 @default.
- W2924156739 cites W2611136914 @default.
- W2924156739 cites W2751422670 @default.
- W2924156739 cites W2772882203 @default.
- W2924156739 cites W2788084076 @default.
- W2924156739 cites W2791704483 @default.
- W2924156739 cites W2803543472 @default.
- W2924156739 cites W2886262373 @default.
- W2924156739 cites W2887709062 @default.
- W2924156739 cites W2889711700 @default.
- W2924156739 cites W2949608212 @default.
- W2924156739 cites W2952720101 @default.
- W2924156739 cites W2952905979 @default.
- W2924156739 cites W2953228110 @default.
- W2924156739 doi "https://doi.org/10.48550/arxiv.1903.08792" @default.
- W2924156739 hasPublicationYear "2019" @default.
- W2924156739 type Work @default.
- W2924156739 sameAs 2924156739 @default.
- W2924156739 citedByCount "13" @default.
- W2924156739 countsByYear W29241567392018 @default.
- W2924156739 countsByYear W29241567392019 @default.
- W2924156739 countsByYear W29241567392020 @default.
- W2924156739 countsByYear W29241567392021 @default.
- W2924156739 crossrefType "posted-content" @default.
- W2924156739 hasAuthorship W2924156739A5002930599 @default.
- W2924156739 hasAuthorship W2924156739A5043415749 @default.
- W2924156739 hasAuthorship W2924156739A5068600217 @default.
- W2924156739 hasAuthorship W2924156739A5089532118 @default.
- W2924156739 hasBestOaLocation W29241567391 @default.
- W2924156739 hasConcept C111919701 @default.
- W2924156739 hasConcept C121332964 @default.
- W2924156739 hasConcept C154945302 @default.
- W2924156739 hasConcept C158622935 @default.
- W2924156739 hasConcept C163716315 @default.
- W2924156739 hasConcept C192921069 @default.
- W2924156739 hasConcept C203479927 @default.
- W2924156739 hasConcept C41008148 @default.
- W2924156739 hasConcept C61326573 @default.
- W2924156739 hasConcept C62520636 @default.
- W2924156739 hasConcept C6557445 @default.
- W2924156739 hasConcept C86803240 @default.
- W2924156739 hasConcept C97541855 @default.
- W2924156739 hasConcept C98045186 @default.
- W2924156739 hasConceptScore W2924156739C111919701 @default.
- W2924156739 hasConceptScore W2924156739C121332964 @default.
- W2924156739 hasConceptScore W2924156739C154945302 @default.
- W2924156739 hasConceptScore W2924156739C158622935 @default.
- W2924156739 hasConceptScore W2924156739C163716315 @default.
- W2924156739 hasConceptScore W2924156739C192921069 @default.
- W2924156739 hasConceptScore W2924156739C203479927 @default.
- W2924156739 hasConceptScore W2924156739C41008148 @default.
- W2924156739 hasConceptScore W2924156739C61326573 @default.
- W2924156739 hasConceptScore W2924156739C62520636 @default.
- W2924156739 hasConceptScore W2924156739C6557445 @default.
- W2924156739 hasConceptScore W2924156739C86803240 @default.
- W2924156739 hasConceptScore W2924156739C97541855 @default.
- W2924156739 hasConceptScore W2924156739C98045186 @default.
- W2924156739 hasLocation W29241567391 @default.
- W2924156739 hasLocation W29241567392 @default.
- W2924156739 hasOpenAccess W2924156739 @default.
- W2924156739 hasPrimaryLocation W29241567391 @default.
- W2924156739 hasRelatedWork W1687991450 @default.
- W2924156739 hasRelatedWork W2017957758 @default.
- W2924156739 hasRelatedWork W2357135621 @default.
- W2924156739 hasRelatedWork W2618318883 @default.
- W2924156739 hasRelatedWork W2924156739 @default.
- W2924156739 hasRelatedWork W2966735560 @default.
- W2924156739 hasRelatedWork W3209976464 @default.
- W2924156739 hasRelatedWork W4210912933 @default.
- W2924156739 hasRelatedWork W4287642554 @default.
- W2924156739 hasRelatedWork W4296754167 @default.
- W2924156739 isParatext "false" @default.
- W2924156739 isRetracted "false" @default.
- W2924156739 magId "2924156739" @default.
- W2924156739 workType "article" @default.