Matches in SemOpenAlex for { <https://semopenalex.org/work/W2912063360> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2912063360 endingPage "2014" @default.
- W2912063360 startingPage "2007" @default.
- W2912063360 abstract "We learn end-to-end point-to-point and pathfollowing navigation behaviors that avoid moving obstacles. These policies receive noisy lidar observations and output robot linear and angular velocities. The policies are trained in small, static environments with AutoRL, an evolutionary automation layer around reinforcement learning (RL) that searches for a deep RL reward and neural network architecture with large-scale hyper-parameter optimization. AutoRL first finds a reward that maximizes task completion and then finds a neural network architecture that maximizes the cumulative of the found reward. Empirical evaluations, both in simulation and on-robot, show that AutoRL policies do not suffer from the catastrophic forgetfulness that plagues many other deep reinforcement learning algorithms, generalize to new environments and moving obstacles, are robust to sensor, actuator, and localization noise, and can serve as robust building blocks for larger navigation tasks. Our path-following and point-to-point policies are, respectively, 23% and 26% more successful than comparison methods across new environments." @default.
- W2912063360 created "2019-02-21" @default.
- W2912063360 creator A5002971435 @default.
- W2912063360 creator A5004095912 @default.
- W2912063360 creator A5043268931 @default.
- W2912063360 creator A5068480093 @default.
- W2912063360 date "2019-04-01" @default.
- W2912063360 modified "2023-10-17" @default.
- W2912063360 title "Learning Navigation Behaviors End-to-End With AutoRL" @default.
- W2912063360 cites W1586102543 @default.
- W2912063360 cites W1972267259 @default.
- W2912063360 cites W2000359213 @default.
- W2912063360 cites W2034936723 @default.
- W2912063360 cites W2051228319 @default.
- W2912063360 cites W2103120971 @default.
- W2912063360 cites W2103285838 @default.
- W2912063360 cites W2105626604 @default.
- W2912063360 cites W2117211893 @default.
- W2912063360 cites W2119112357 @default.
- W2912063360 cites W2128990851 @default.
- W2912063360 cites W2145339207 @default.
- W2912063360 cites W2167052694 @default.
- W2912063360 cites W2178108034 @default.
- W2912063360 cites W2334752150 @default.
- W2912063360 cites W2411929833 @default.
- W2912063360 cites W2524241275 @default.
- W2912063360 cites W2732547613 @default.
- W2912063360 cites W2962917939 @default.
- W2912063360 cites W2963252944 @default.
- W2912063360 cites W3021208093 @default.
- W2912063360 cites W3124420883 @default.
- W2912063360 doi "https://doi.org/10.1109/lra.2019.2899918" @default.
- W2912063360 hasPublicationYear "2019" @default.
- W2912063360 type Work @default.
- W2912063360 sameAs 2912063360 @default.
- W2912063360 citedByCount "166" @default.
- W2912063360 countsByYear W29120633602019 @default.
- W2912063360 countsByYear W29120633602020 @default.
- W2912063360 countsByYear W29120633602021 @default.
- W2912063360 countsByYear W29120633602022 @default.
- W2912063360 countsByYear W29120633602023 @default.
- W2912063360 crossrefType "journal-article" @default.
- W2912063360 hasAuthorship W2912063360A5002971435 @default.
- W2912063360 hasAuthorship W2912063360A5004095912 @default.
- W2912063360 hasAuthorship W2912063360A5043268931 @default.
- W2912063360 hasAuthorship W2912063360A5068480093 @default.
- W2912063360 hasBestOaLocation W29120633601 @default.
- W2912063360 hasConcept C115961682 @default.
- W2912063360 hasConcept C127413603 @default.
- W2912063360 hasConcept C154945302 @default.
- W2912063360 hasConcept C201995342 @default.
- W2912063360 hasConcept C2524010 @default.
- W2912063360 hasConcept C2780451532 @default.
- W2912063360 hasConcept C28719098 @default.
- W2912063360 hasConcept C33923547 @default.
- W2912063360 hasConcept C41008148 @default.
- W2912063360 hasConcept C50644808 @default.
- W2912063360 hasConcept C74296488 @default.
- W2912063360 hasConcept C81074085 @default.
- W2912063360 hasConcept C90509273 @default.
- W2912063360 hasConcept C97541855 @default.
- W2912063360 hasConcept C99498987 @default.
- W2912063360 hasConceptScore W2912063360C115961682 @default.
- W2912063360 hasConceptScore W2912063360C127413603 @default.
- W2912063360 hasConceptScore W2912063360C154945302 @default.
- W2912063360 hasConceptScore W2912063360C201995342 @default.
- W2912063360 hasConceptScore W2912063360C2524010 @default.
- W2912063360 hasConceptScore W2912063360C2780451532 @default.
- W2912063360 hasConceptScore W2912063360C28719098 @default.
- W2912063360 hasConceptScore W2912063360C33923547 @default.
- W2912063360 hasConceptScore W2912063360C41008148 @default.
- W2912063360 hasConceptScore W2912063360C50644808 @default.
- W2912063360 hasConceptScore W2912063360C74296488 @default.
- W2912063360 hasConceptScore W2912063360C81074085 @default.
- W2912063360 hasConceptScore W2912063360C90509273 @default.
- W2912063360 hasConceptScore W2912063360C97541855 @default.
- W2912063360 hasConceptScore W2912063360C99498987 @default.
- W2912063360 hasFunder F4320309327 @default.
- W2912063360 hasIssue "2" @default.
- W2912063360 hasLocation W29120633601 @default.
- W2912063360 hasLocation W29120633602 @default.
- W2912063360 hasOpenAccess W2912063360 @default.
- W2912063360 hasPrimaryLocation W29120633601 @default.
- W2912063360 hasRelatedWork W2031695474 @default.
- W2912063360 hasRelatedWork W2138720691 @default.
- W2912063360 hasRelatedWork W2151749779 @default.
- W2912063360 hasRelatedWork W2586732548 @default.
- W2912063360 hasRelatedWork W3049728571 @default.
- W2912063360 hasRelatedWork W3179968364 @default.
- W2912063360 hasRelatedWork W3196421258 @default.
- W2912063360 hasRelatedWork W4306904969 @default.
- W2912063360 hasRelatedWork W4362501864 @default.
- W2912063360 hasRelatedWork W4380318855 @default.
- W2912063360 hasVolume "4" @default.
- W2912063360 isParatext "false" @default.
- W2912063360 isRetracted "false" @default.
- W2912063360 magId "2912063360" @default.
- W2912063360 workType "article" @default.