乐胖代购免代理版

{"id":"https://openalex.org/W2913273311","doi":"https://doi.org/10.1109/humanoids.2018.8624949","title":"Learning Sequential Decision Tasks for Robot Manipulation with Abstract Markov Decision Processes and Demonstration-Guided Exploration","display_name":"Learning Sequential Decision Tasks for Robot Manipulation with Abstract Markov Decision Processes and Demonstration-Guided Exploration","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2913273311","doi":"https://doi.org/10.1109/humanoids.2018.8624949","mag":"2913273311"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2018.8624949","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/A5030081726","display_name":"David Kent","orcid":"https://orcid.org/0000-0002-5418-3602"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kent","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085889685","display_name":"Siddhartha Banerjee","orcid":"https://orcid.org/0000-0002-8954-4578"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Banerjee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033265891","display_name":"Sonia Chernova","orcid":"https://orcid.org/0000-0001-6320-0825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sonia Chernova","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.184,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":3,"citation_normalized_percentile":{"value":0.195361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":74,"max":77},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994,"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":0.9994,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9988,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11159","display_name":"Manufacturing Process and Optimization","score":0.9466,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation","score":0.6098961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77696705},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7497359},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.73902935},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6558726},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6098961},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6067372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.59981},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4878838},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.47966197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43058968},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3464586},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2018.8624949","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.78}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":21,"referenced_works":["https://openalex.org/W11497584","https://openalex.org/W174404835","https://openalex.org/W1969897050","https://openalex.org/W1986014385","https://openalex.org/W2007770355","https://openalex.org/W2062122188","https://openalex.org/W2101355568","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2134153324","https://openalex.org/W2137375617","https://openalex.org/W2160371091","https://openalex.org/W2162227979","https://openalex.org/W2285390452","https://openalex.org/W2314354400","https://openalex.org/W2749153024","https://openalex.org/W2758731390","https://openalex.org/W2949267040","https://openalex.org/W2963262099","https://openalex.org/W2963888186","https://openalex.org/W2964227312"],"related_works":["https://openalex.org/W3168977894","https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2341346307","https://openalex.org/W2145363145","https://openalex.org/W1985560493","https://openalex.org/W187740018","https://openalex.org/W1626977535"],"abstract_inverted_index":{"Solving":[0],"high-level":[1],"sequential":[2,20],"decision":[3,21],"tasks":[4],"situated":[5],"on":[6,170],"physical":[7,172],"robots":[8,24],"is":[9,31,121],"a":[10,74,87,113,171],"challenging":[11],"problem.":[12],"Reinforcement":[13],"learning,":[14],"the":[15,47,57,64,150,165],"standard":[16],"paradigm":[17],"for":[18,78,91,123,141],"solving":[19,79,124],"problems,":[22],"allows":[23],"to":[25,33,50,53,156],"learn":[26],"directly":[27],"from":[28,102],"experience,":[29],"but":[30],"ill-equipped":[32],"deal":[34],"with":[35],"issues":[36],"of":[37,59],"scalability":[38],"and":[39,63,99,109,127,131,139,162],"uncertainty":[40],"introduced":[41],"by":[42,68,97],"real-world":[43],"tasks.":[44],"We":[45,72,105,147],"reformulate":[46],"problem":[48],"representation":[49,108,120],"better":[51],"apply":[52],"robot":[54],"manipulation":[55],"using":[56],"relations":[58],"Object-Oriented":[60],"MDPs":[61,70],"(OO-MDPs)":[62],"hierarchical":[65,119],"structure":[66],"provided":[67],"Abstract":[69],"(AMDPs).":[71],"present":[73],"relation-based":[75],"AMDP":[76,93,144],"formulation":[77],"tabletop":[80,158],"organizational":[81,159],"packing":[82,160],"tasks,":[83,126,161],"as":[84,86],"well":[85],"demonstration-guided":[88],"exploration":[89,133],"algorithm":[90],"learning":[92,101,110,143],"transition":[94,145],"functions":[95],"inspired":[96],"state-":[98,130],"action-centric":[100,132],"demonstration":[103],"approaches.":[104],"evaluate":[106],"our":[107,118,129],"methods":[111,135],"in":[112],"simulated":[114],"environment,":[115],"showing":[116],"that":[117,128,149,164],"suitable":[122],"complex":[125],"biasing":[134],"are":[136],"both":[137],"effective":[138],"complementary":[140],"efficiently":[142],"functions.":[146],"show":[148],"learned":[151],"policy":[152,166],"can":[153,167],"be":[154,168],"transferred":[155],"different":[157],"validate":[163],"realized":[169],"system.":[173]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2913273311","counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2025-01-18T03:14:01.854869","created_date":"2019-02-21"}