FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3004416026> ?p ?o ?g. }

• W3004416026 abstract "Humans can learn many novel tasks from a very small number (1--5) of demonstrations, in stark contrast to the data requirements of nearly tabula rasa deep learning methods. We propose an expressive class of policies, a strong but general prior, and a learning algorithm that, together, can learn interesting policies from very few examples. We represent policies as logical combinations of programs drawn from a domain-specific language (DSL), define a prior over policies with a probabilistic grammar, and derive an approximate Bayesian inference algorithm to learn policies from demonstrations. In experiments, we study five strategy games played on a 2D grid with one shared DSL. After a few demonstrations of each game, the inferred policies generalize to new game instances that differ substantially from the demonstrations. Our policy learning is 20--1,000x more data efficient than convolutional and fully convolutional policy learning and many orders of magnitude more computationally efficient than vanilla program induction. We argue that the proposed method is an apt choice for tasks that have scarce training data and feature significant, structured variation between task instances." @default.
• W3004416026 created "2020-02-07" @default.
• W3004416026 creator A5012862284 @default.
• W3004416026 creator A5018071113 @default.
• W3004416026 creator A5023131292 @default.
• W3004416026 creator A5047843932 @default.
• W3004416026 creator A5073565150 @default.
• W3004416026 date "2019-04-12" @default.
• W3004416026 modified "2023-09-23" @default.
• W3004416026 title "Few-Shot Bayesian Imitation Learning with Logical Program Policies" @default.
• W3004416026 cites W1504619461 @default.
• W3004416026 cites W1508965297 @default.
• W3004416026 cites W1574901103 @default.
• W3004416026 cites W1580472141 @default.
• W3004416026 cites W168365783 @default.
• W3004416026 cites W1766442844 @default.
• W3004416026 cites W1903029394 @default.
• W3004416026 cites W199176224 @default.
• W3004416026 cites W1999874108 @default.
• W3004416026 cites W2054658115 @default.
• W3004416026 cites W2064229486 @default.
• W3004416026 cites W2089561656 @default.
• W3004416026 cites W2094878426 @default.
• W3004416026 cites W2101234009 @default.
• W3004416026 cites W2113475501 @default.
• W3004416026 cites W2119678437 @default.
• W3004416026 cites W2142336306 @default.
• W3004416026 cites W2148112459 @default.
• W3004416026 cites W2148886952 @default.
• W3004416026 cites W2149706766 @default.
• W3004416026 cites W2154055561 @default.
• W3004416026 cites W2194321275 @default.
• W3004416026 cites W2211996086 @default.
• W3004416026 cites W2245825236 @default.
• W3004416026 cites W2246013387 @default.
• W3004416026 cites W2340316421 @default.
• W3004416026 cites W2498991332 @default.
• W3004416026 cites W2603456259 @default.
• W3004416026 cites W2624780181 @default.
• W3004416026 cites W2740254106 @default.
• W3004416026 cites W2755546070 @default.
• W3004416026 cites W2788927107 @default.
• W3004416026 cites W2796284132 @default.
• W3004416026 cites W2804838341 @default.
• W3004416026 cites W2891902226 @default.
• W3004416026 cites W2905304202 @default.
• W3004416026 cites W2949084598 @default.
• W3004416026 cites W2953081964 @default.
• W3004416026 cites W2963094133 @default.
• W3004416026 cites W2963099939 @default.
• W3004416026 cites W2963376229 @default.
• W3004416026 cites W2964055695 @default.
• W3004416026 cites W2964311356 @default.
• W3004416026 cites W2979490629 @default.
• W3004416026 cites W3121299688 @default.
• W3004416026 cites W1531196559 @default.
• W3004416026 hasPublicationYear "2019" @default.
• W3004416026 type Work @default.
• W3004416026 sameAs 3004416026 @default.
• W3004416026 citedByCount "1" @default.
• W3004416026 countsByYear W30044160262020 @default.
• W3004416026 crossrefType "posted-content" @default.
• W3004416026 hasAuthorship W3004416026A5012862284 @default.
• W3004416026 hasAuthorship W3004416026A5018071113 @default.
• W3004416026 hasAuthorship W3004416026A5023131292 @default.
• W3004416026 hasAuthorship W3004416026A5047843932 @default.
• W3004416026 hasAuthorship W3004416026A5073565150 @default.
• W3004416026 hasConcept C104317684 @default.
• W3004416026 hasConcept C107673813 @default.
• W3004416026 hasConcept C112313634 @default.
• W3004416026 hasConcept C119857082 @default.
• W3004416026 hasConcept C127716648 @default.
• W3004416026 hasConcept C154945302 @default.
• W3004416026 hasConcept C162324750 @default.
• W3004416026 hasConcept C185592680 @default.
• W3004416026 hasConcept C187736073 @default.
• W3004416026 hasConcept C188082640 @default.
• W3004416026 hasConcept C2776214188 @default.
• W3004416026 hasConcept C2780451532 @default.
• W3004416026 hasConcept C41008148 @default.
• W3004416026 hasConcept C49937458 @default.
• W3004416026 hasConcept C55493867 @default.
• W3004416026 hasConceptScore W3004416026C104317684 @default.
• W3004416026 hasConceptScore W3004416026C107673813 @default.
• W3004416026 hasConceptScore W3004416026C112313634 @default.
• W3004416026 hasConceptScore W3004416026C119857082 @default.
• W3004416026 hasConceptScore W3004416026C127716648 @default.
• W3004416026 hasConceptScore W3004416026C154945302 @default.
• W3004416026 hasConceptScore W3004416026C162324750 @default.
• W3004416026 hasConceptScore W3004416026C185592680 @default.
• W3004416026 hasConceptScore W3004416026C187736073 @default.
• W3004416026 hasConceptScore W3004416026C188082640 @default.
• W3004416026 hasConceptScore W3004416026C2776214188 @default.
• W3004416026 hasConceptScore W3004416026C2780451532 @default.
• W3004416026 hasConceptScore W3004416026C41008148 @default.
• W3004416026 hasConceptScore W3004416026C49937458 @default.
• W3004416026 hasConceptScore W3004416026C55493867 @default.
• W3004416026 hasOpenAccess W3004416026 @default.
• W3004416026 hasRelatedWork W2261891975 @default.
• W3004416026 hasRelatedWork W2416453010 @default.

• next