乐胖代购免代理版

{"id":"https://openalex.org/W3207514672","doi":"https://doi.org/10.1109/icra48506.2021.9561435","title":"Solving Markov Decision Processes with Partial State Abstractions","display_name":"Solving Markov Decision Processes with Partial State Abstractions","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3207514672","doi":"https://doi.org/10.1109/icra48506.2021.9561435","mag":"3207514672"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032977536","display_name":"Samer B. Nashed","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samer B. Nashed","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080873677","display_name":"Justin Svegliato","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin Svegliato","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072749095","display_name":"Matteo Brucato","orcid":"https://orcid.org/0000-0003-2730-6432"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matteo Brucato","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047063533","display_name":"Connor Basich","orcid":"https://orcid.org/0000-0001-9522-5277"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Connor Basich","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112501188","display_name":"Rod Grupen","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rod Grupen","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027224308","display_name":"Shlomo Zilberstein","orcid":"https://orcid.org/0000-0001-9817-7848"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shlomo Zilberstein","raw_affiliation_strings":["College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"College of Information and Computer Sciences, University of Massachusetts, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.508,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.999914,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":78,"max":81},"biblio":{"volume":null,"issue":null,"first_page":"813","last_page":"819"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9986,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.9976,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81220996},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.79154474},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7539057},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.707837},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.66225827},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.579422},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5655251},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5561618},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.480462},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.41691187},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.39533296},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36490133},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.36190218},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23345366},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.21254039},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11317435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.101448804},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.083859146},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.76}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":48,"referenced_works":["https://openalex.org/W127341816","https://openalex.org/W1497650279","https://openalex.org/W1534331386","https://openalex.org/W1553182805","https://openalex.org/W1591992921","https://openalex.org/W1964535365","https://openalex.org/W1988217924","https://openalex.org/W2009533501","https://openalex.org/W204092060","https://openalex.org/W2058735307","https://openalex.org/W2105757562","https://openalex.org/W2107664584","https://openalex.org/W2109634117","https://openalex.org/W2121517924","https://openalex.org/W2124477018","https://openalex.org/W2153267861","https://openalex.org/W2159961872","https://openalex.org/W2169324952","https://openalex.org/W2170233819","https://openalex.org/W2170400507","https://openalex.org/W2213183462","https://openalex.org/W2219400200","https://openalex.org/W2295864763","https://openalex.org/W2341150500","https://openalex.org/W2341171179","https://openalex.org/W2397240726","https://openalex.org/W2400287765","https://openalex.org/W2403355785","https://openalex.org/W2568972189","https://openalex.org/W2578761269","https://openalex.org/W2605325129","https://openalex.org/W2730780157","https://openalex.org/W2739957299","https://openalex.org/W2946767964","https://openalex.org/W2952544286","https://openalex.org/W2962872744","https://openalex.org/W3000078855","https://openalex.org/W3003428332","https://openalex.org/W3003994825","https://openalex.org/W3037099454","https://openalex.org/W3037614835","https://openalex.org/W3103882218","https://openalex.org/W3104102736","https://openalex.org/W3176562834","https://openalex.org/W4199186","https://openalex.org/W4237591687","https://openalex.org/W4289236638","https://openalex.org/W4320930694"],"related_works":["https://openalex.org/W52153049","https://openalex.org/W4323315247","https://openalex.org/W3208638985","https://openalex.org/W3169161914","https://openalex.org/W2951545791","https://openalex.org/W2294884454","https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609"],"abstract_inverted_index":{"Autonomous":[0],"systems":[1],"often":[2],"use":[3],"approximate":[4],"planners":[5,20],"that":[6,48,66,90,128],"exploit":[7],"state":[8],"abstractions":[9],"to":[10,25,56,75,132],"solve":[11],"large":[12,133],"MDPs":[13],"in":[14,29,119,135],"real-time":[15],"decision-making":[16],"problems.":[17],"However,":[18],"these":[19],"can":[21],"eliminate":[22],"details":[23,59],"needed":[24],"produce":[26],"effective":[27],"behavior":[28],"autonomous":[30,120],"systems.":[31,121],"We":[32],"therefore":[33],"propose":[34],"a":[35,38,43,51,61,69,83,86,112,125],"novel":[36],"model,":[37],"partially":[39,87],"abstract":[40,46,73,88,98,107],"MDP,":[41],"with":[42,110],"set":[44,52,62,70],"of":[45,53,63,71,85],"states":[47,55,65,74],"each":[49],"compress":[50],"ground":[54,64,94],"condense":[57],"irrelevant":[58],"and":[60,96,100,117],"expand":[67],"from":[68],"expanded":[72],"retain":[76],"relevant":[77],"details.":[78],"This":[79],"papers":[80],"offers":[81],"(1)":[82],"definition":[84],"MDP":[89,95,99,108],"(2)":[91],"generalizes":[92],"its":[93,97,106],"exhibits":[101],"bounded":[102],"optimality":[103],"depending":[104],"on":[105],"along":[109],"(3)":[111],"lazy":[113],"algorithm":[114],"for":[115],"planning":[116],"execution":[118],"The":[122],"result":[123],"is":[124],"scalable":[126],"approach":[127],"computes":[129],"near-optimal":[130],"solutions":[131],"problems":[134],"minutes":[136],"rather":[137],"than":[138],"hours.":[139]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3207514672","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-01-07T08:28:50.425610","created_date":"2021-10-25"}