FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3151183549> ?p ?o ?g. }

• W3151183549 abstract "A key challenge in Imitation Learning (IL) is that optimal state actions demonstrations are difficult for the teacher to provide. For example in robotics, providing kinesthetic demonstrations on a robotic manipulator requires the teacher to control multiple degrees of freedom at once. The difficulty of requiring optimal state action demonstrations limits the space of problems where the teacher can provide quality feedback. As an alternative to state action demonstrations, the teacher can provide corrective feedback such as their preferences or rewards. Prior work has created algorithms designed to learn from specific types of noisy feedback, but across teachers and tasks different forms of feedback may be required. Instead we propose that in order to learn from a diversity of scenarios we need to learn from a variety of feedback. To learn from a variety of feedback we make the following insight: the teacher's cost function is latent and we can model a stream of feedback as a stream of loss functions. We then use any online learning algorithm to minimize the sum of these losses. With this insight we can learn from a diversity of feedback that is weakly correlated with the teacher's true cost function. We unify prior work into a general corrective feedback meta-algorithm and show that regardless of feedback we can obtain the same regret bounds. We demonstrate our approach by learning to perform a household navigation task on a robotic racecar platform. Our results show that our approach can learn quickly from a variety of noisy feedback." @default.
• W3151183549 created "2021-04-13" @default.
• W3151183549 creator A5038162737 @default.
• W3151183549 creator A5057995939 @default.
• W3151183549 creator A5077719529 @default.
• W3151183549 date "2021-04-02" @default.
• W3151183549 modified "2023-09-27" @default.
• W3151183549 title "Learning Online from Corrective Feedback: A Meta-Algorithm for Robotics." @default.
• W3151183549 cites W1737105075 @default.
• W3151183549 cites W1837766154 @default.
• W3151183549 cites W1990609757 @default.
• W3151183549 cites W2127572219 @default.
• W3151183549 cites W2142774925 @default.
• W3151183549 cites W2159574904 @default.
• W3151183549 cites W2161872510 @default.
• W3151183549 cites W230475630 @default.
• W3151183549 cites W2580300496 @default.
• W3151183549 cites W2769520592 @default.
• W3151183549 cites W2794908222 @default.
• W3151183549 cites W2889990052 @default.
• W3151183549 cites W2911719076 @default.
• W3151183549 cites W2912748147 @default.
• W3151183549 cites W2915070458 @default.
• W3151183549 cites W2950735232 @default.
• W3151183549 cites W2953127211 @default.
• W3151183549 cites W2962957031 @default.
• W3151183549 cites W2963796903 @default.
• W3151183549 cites W2964263543 @default.
• W3151183549 cites W2969748094 @default.
• W3151183549 cites W607505555 @default.
• W3151183549 hasPublicationYear "2021" @default.
• W3151183549 type Work @default.
• W3151183549 sameAs 3151183549 @default.
• W3151183549 citedByCount "0" @default.
• W3151183549 crossrefType "posted-content" @default.
• W3151183549 hasAuthorship W3151183549A5038162737 @default.
• W3151183549 hasAuthorship W3151183549A5057995939 @default.
• W3151183549 hasAuthorship W3151183549A5077719529 @default.
• W3151183549 hasConcept C107457646 @default.
• W3151183549 hasConcept C119857082 @default.
• W3151183549 hasConcept C121332964 @default.
• W3151183549 hasConcept C127413603 @default.
• W3151183549 hasConcept C136197465 @default.
• W3151183549 hasConcept C14036430 @default.
• W3151183549 hasConcept C145420912 @default.
• W3151183549 hasConcept C154945302 @default.
• W3151183549 hasConcept C201995342 @default.
• W3151183549 hasConcept C26517878 @default.
• W3151183549 hasConcept C2779305910 @default.
• W3151183549 hasConcept C2780451532 @default.
• W3151183549 hasConcept C2780791683 @default.
• W3151183549 hasConcept C33923547 @default.
• W3151183549 hasConcept C34413123 @default.
• W3151183549 hasConcept C38652104 @default.
• W3151183549 hasConcept C41008148 @default.
• W3151183549 hasConcept C50817715 @default.
• W3151183549 hasConcept C62520636 @default.
• W3151183549 hasConcept C78458016 @default.
• W3151183549 hasConcept C86803240 @default.
• W3151183549 hasConcept C90509273 @default.
• W3151183549 hasConceptScore W3151183549C107457646 @default.
• W3151183549 hasConceptScore W3151183549C119857082 @default.
• W3151183549 hasConceptScore W3151183549C121332964 @default.
• W3151183549 hasConceptScore W3151183549C127413603 @default.
• W3151183549 hasConceptScore W3151183549C136197465 @default.
• W3151183549 hasConceptScore W3151183549C14036430 @default.
• W3151183549 hasConceptScore W3151183549C145420912 @default.
• W3151183549 hasConceptScore W3151183549C154945302 @default.
• W3151183549 hasConceptScore W3151183549C201995342 @default.
• W3151183549 hasConceptScore W3151183549C26517878 @default.
• W3151183549 hasConceptScore W3151183549C2779305910 @default.
• W3151183549 hasConceptScore W3151183549C2780451532 @default.
• W3151183549 hasConceptScore W3151183549C2780791683 @default.
• W3151183549 hasConceptScore W3151183549C33923547 @default.
• W3151183549 hasConceptScore W3151183549C34413123 @default.
• W3151183549 hasConceptScore W3151183549C38652104 @default.
• W3151183549 hasConceptScore W3151183549C41008148 @default.
• W3151183549 hasConceptScore W3151183549C50817715 @default.
• W3151183549 hasConceptScore W3151183549C62520636 @default.
• W3151183549 hasConceptScore W3151183549C78458016 @default.
• W3151183549 hasConceptScore W3151183549C86803240 @default.
• W3151183549 hasConceptScore W3151183549C90509273 @default.
• W3151183549 hasLocation W31511835491 @default.
• W3151183549 hasOpenAccess W3151183549 @default.
• W3151183549 hasPrimaryLocation W31511835491 @default.
• W3151183549 hasRelatedWork W2068100625 @default.
• W3151183549 hasRelatedWork W2165081250 @default.
• W3151183549 hasRelatedWork W2471581187 @default.
• W3151183549 hasRelatedWork W2513373085 @default.
• W3151183549 hasRelatedWork W2528734395 @default.
• W3151183549 hasRelatedWork W2550648340 @default.
• W3151183549 hasRelatedWork W2784165037 @default.
• W3151183549 hasRelatedWork W2911719076 @default.
• W3151183549 hasRelatedWork W2921379287 @default.
• W3151183549 hasRelatedWork W2949115740 @default.
• W3151183549 hasRelatedWork W2952325095 @default.
• W3151183549 hasRelatedWork W2963391602 @default.
• W3151183549 hasRelatedWork W2963633674 @default.
• W3151183549 hasRelatedWork W3002128304 @default.
• W3151183549 hasRelatedWork W3035173916 @default.

• next