FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2770014065> ?p ?o ?g. }

• W2770014065 abstract "Robot planning is the process of selecting a sequence of actions that optimize for a task specific objective. The optimal solutions to such tasks are heavily influenced by the implicit structure in the environment, i.e. the configuration of objects in the world. State-of-the-art planning approaches, however, do not exploit this structure, thereby expending valuable effort searching the action space instead of focusing on potentially good actions. In this paper, we address the problem of enabling planners to adapt their search strategies by inferring such good actions in an efficient manner using only the information uncovered by the search up until that time. We formulate this as a problem of sequential decision making under uncertainty where at a given iteration a planning policy must map the state of the search to a planning action. Unfortunately, the training process for such partial information based policies is slow to converge and susceptible to poor local minima. Our key insight is that if we could fully observe the underlying world map, we would easily be able to disambiguate between good and bad actions. We hence present a novel data-driven imitation learning framework to efficiently train planning policies by imitating a clairvoyant oracle - an oracle that at train time has full knowledge about the world map and can compute optimal decisions. We leverage the fact that for planning problems, such oracles can be efficiently computed and derive performance guarantees for the learnt policy. We examine two important domains that rely on partial information based policies - informative path planning and search based motion planning. We validate the approach on a spectrum of environments for both problem domains, including experiments on a real UAV, and show that the learnt policy consistently outperforms state-of-the-art algorithms." @default.
• W2770014065 created "2017-12-04" @default.
• W2770014065 creator A5017774267 @default.
• W2770014065 creator A5020666821 @default.
• W2770014065 creator A5032584934 @default.
• W2770014065 creator A5051080429 @default.
• W2770014065 creator A5055069190 @default.
• W2770014065 creator A5057995939 @default.
• W2770014065 creator A5078150431 @default.
• W2770014065 date "2017-11-17" @default.
• W2770014065 modified "2023-09-22" @default.
• W2770014065 title "Data-driven Planning via Imitation Learning" @default.
• W2770014065 cites W1140243306 @default.
• W2770014065 cites W1484557735 @default.
• W2770014065 cites W1505937442 @default.
• W2770014065 cites W1516027685 @default.
• W2770014065 cites W1517928915 @default.
• W2770014065 cites W1519170695 @default.
• W2770014065 cites W1545688112 @default.
• W2770014065 cites W1577296257 @default.
• W2770014065 cites W1601974704 @default.
• W2770014065 cites W1636455720 @default.
• W2770014065 cites W174354460 @default.
• W2770014065 cites W1765105432 @default.
• W2770014065 cites W1845961848 @default.
• W2770014065 cites W1923344279 @default.
• W2770014065 cites W1941409503 @default.
• W2770014065 cites W1949377792 @default.
• W2770014065 cites W1971086298 @default.
• W2770014065 cites W1975463331 @default.
• W2770014065 cites W1977070092 @default.
• W2770014065 cites W1977655452 @default.
• W2770014065 cites W1999874108 @default.
• W2770014065 cites W2000359213 @default.
• W2770014065 cites W2023148409 @default.
• W2770014065 cites W2098774185 @default.
• W2770014065 cites W2099430963 @default.
• W2770014065 cites W2106370322 @default.
• W2770014065 cites W2113029345 @default.
• W2770014065 cites W2114235770 @default.
• W2770014065 cites W2124595631 @default.
• W2770014065 cites W2127107099 @default.
• W2770014065 cites W2136445059 @default.
• W2770014065 cites W2138597123 @default.
• W2770014065 cites W2142624263 @default.
• W2770014065 cites W2146140624 @default.
• W2770014065 cites W2151239055 @default.
• W2770014065 cites W2158118484 @default.
• W2770014065 cites W2158282517 @default.
• W2770014065 cites W2161521419 @default.
• W2770014065 cites W2166295994 @default.
• W2770014065 cites W2168359464 @default.
• W2770014065 cites W2171084228 @default.
• W2770014065 cites W2176263492 @default.
• W2770014065 cites W2183805903 @default.
• W2770014065 cites W2187544948 @default.
• W2770014065 cites W2201581102 @default.
• W2770014065 cites W2257979135 @default.
• W2770014065 cites W2264407643 @default.
• W2770014065 cites W2283534560 @default.
• W2770014065 cites W2290104316 @default.
• W2770014065 cites W2313274380 @default.
• W2770014065 cites W2336416123 @default.
• W2770014065 cites W2336687883 @default.
• W2770014065 cites W2342662072 @default.
• W2770014065 cites W2404076338 @default.
• W2770014065 cites W2405683058 @default.
• W2770014065 cites W2408221314 @default.
• W2770014065 cites W2410983263 @default.
• W2770014065 cites W2413963660 @default.
• W2770014065 cites W2462851002 @default.
• W2770014065 cites W2527551115 @default.
• W2770014065 cites W2569188995 @default.
• W2770014065 cites W2600009170 @default.
• W2770014065 cites W2611243847 @default.
• W2770014065 cites W2729294377 @default.
• W2770014065 cites W2737130609 @default.
• W2770014065 cites W2739245227 @default.
• W2770014065 cites W2745868649 @default.
• W2770014065 cites W2754453099 @default.
• W2770014065 cites W2950735232 @default.
• W2770014065 cites W2951249809 @default.
• W2770014065 cites W2952523895 @default.
• W2770014065 cites W2952840881 @default.
• W2770014065 cites W2953027552 @default.
• W2770014065 cites W2962725800 @default.
• W2770014065 cites W2962795549 @default.
• W2770014065 cites W2962938178 @default.
• W2770014065 cites W2962957031 @default.
• W2770014065 cites W2963128534 @default.
• W2770014065 cites W2963241557 @default.
• W2770014065 cites W3021035068 @default.
• W2770014065 cites W60337842 @default.
• W2770014065 hasPublicationYear "2017" @default.
• W2770014065 type Work @default.
• W2770014065 sameAs 2770014065 @default.
• W2770014065 citedByCount "3" @default.
• W2770014065 countsByYear W27700140652018 @default.
• W2770014065 countsByYear W27700140652019 @default.
• W2770014065 crossrefType "posted-content" @default.

• next