{"id":"https://openalex.org/W3207906202","doi":"https://doi.org/10.1109/icra48506.2021.9561917","title":"Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty","display_name":"Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3207906202","doi":"https://doi.org/10.1109/icra48506.2021.9561917","mag":"3207906202"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5053041702","display_name":"Fanfei Chen","orcid":"https://orcid.org/0000-0001-6724-3515"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fanfei Chen","raw_affiliation_strings":["Department of Mechanical Engineering, Stevens Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stevens Institute of Technology, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060201714","display_name":"Paul Szenher","orcid":"https://orcid.org/0009-0009-3835-5433"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Szenher","raw_affiliation_strings":["Department of Mechanical Engineering, Stevens Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stevens Institute of Technology, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016931059","display_name":"Yewei Huang","orcid":"https://orcid.org/0000-0002-2505-6022"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yewei Huang","raw_affiliation_strings":["Department of Mechanical Engineering, Stevens Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stevens Institute of Technology, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090819950","display_name":"Jinkun Wang","orcid":"https://orcid.org/0000-0001-7030-5035"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinkun Wang","raw_affiliation_strings":["Department of Mechanical Engineering, Stevens Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stevens Institute of Technology, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035486248","display_name":"Tixiao Shan","orcid":"https://orcid.org/0000-0003-0988-0799"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tixiao Shan","raw_affiliation_strings":["Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562163","display_name":"Shi Bai","orcid":"https://orcid.org/0000-0002-6081-3084"},"institutions":[{"id":"https://openalex.org/I4210128969","display_name":"Alphabet (United States)","ror":"https://ror.org/02e9yx751","country_code":"US","type":"company","lineage":["https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi Bai","raw_affiliation_strings":["Wing, Alphabet Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wing, Alphabet Inc","institution_ids":["https://openalex.org/I4210128969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044251670","display_name":"Brendan Englot","orcid":"https://orcid.org/0000-0002-7966-2917"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Englot","raw_affiliation_strings":["Department of Mechanical Engineering, Stevens Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stevens Institute of Technology, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0514,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.89641394,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5193","last_page":"5199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8515911102294922},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8052573800086975},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5894186496734619},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5618546605110168},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5155777335166931},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4907296895980835},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4565120041370392},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4429527521133423},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4395347237586975},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4368158280849457},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37909215688705444},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3491376042366028}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8515911102294922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052573800086975},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5894186496734619},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618546605110168},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5155777335166931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4907296895980835},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4565120041370392},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4429527521133423},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4395347237586975},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4368158280849457},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37909215688705444},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3491376042366028},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1573725801","https://openalex.org/W1684737195","https://openalex.org/W1901129140","https://openalex.org/W1968315983","https://openalex.org/W1988757690","https://openalex.org/W2056554710","https://openalex.org/W2107667896","https://openalex.org/W2115126368","https://openalex.org/W2116341502","https://openalex.org/W2145339207","https://openalex.org/W2182229738","https://openalex.org/W2205975260","https://openalex.org/W2346044757","https://openalex.org/W2527172881","https://openalex.org/W2564666437","https://openalex.org/W2737993726","https://openalex.org/W2749807327","https://openalex.org/W2770679144","https://openalex.org/W2771342126","https://openalex.org/W2785948534","https://openalex.org/W2804072623","https://openalex.org/W2805516822","https://openalex.org/W2908729504","https://openalex.org/W2910054127","https://openalex.org/W2918342466","https://openalex.org/W2952832237","https://openalex.org/W2962812366","https://openalex.org/W2963207497","https://openalex.org/W2964015378","https://openalex.org/W2990723925","https://openalex.org/W2996793228","https://openalex.org/W3003778718","https://openalex.org/W3098085399","https://openalex.org/W3099455272","https://openalex.org/W3133136962","https://openalex.org/W4213266403","https://openalex.org/W4249753958","https://openalex.org/W4288419263","https://openalex.org/W4322614752","https://openalex.org/W6639824700","https://openalex.org/W6647490918","https://openalex.org/W6685664056","https://openalex.org/W6688146251","https://openalex.org/W6726873649","https://openalex.org/W6731654439","https://openalex.org/W6741521816","https://openalex.org/W6743756900","https://openalex.org/W6746348303","https://openalex.org/W6746886387","https://openalex.org/W6747769025","https://openalex.org/W6751796012","https://openalex.org/W6757634740","https://openalex.org/W6760045743","https://openalex.org/W6770450912","https://openalex.org/W6771687660","https://openalex.org/W6772637341","https://openalex.org/W6781486315","https://openalex.org/W6809315833"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2120009678","https://openalex.org/W2912947802","https://openalex.org/W2037601570","https://openalex.org/W2123856982","https://openalex.org/W1530089576"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"the":[3,68,91],"problem":[4],"of":[5,94],"autonomous":[6],"exploration":[7,27,133],"under":[8],"localization":[9],"uncertainty":[10],"for":[11,23],"a":[12,21,25,30,113,141,156,161],"mobile":[13],"robot":[14],"with":[15,86,123],"3D":[16],"range":[17],"sensing.":[18],"We":[19,111],"present":[20],"framework":[22],"self-learning":[24],"high-performance":[26],"policy":[28],"in":[29,48,71,84,121,146,155,169],"single":[31,157],"simulation":[32,158,174],"environment,":[33,159],"and":[34,57,73,164,176],"transferring":[35],"it":[36,77],"to":[37,60,64,80,89,108,139,172],"other":[38,173],"environments,":[39],"which":[40,151],"may":[41],"be":[42],"physical":[43],"or":[44],"virtual.":[45],"Recent":[46],"work":[47],"transfer":[49,171],"learning":[50],"achieves":[51],"encouraging":[52],"performance":[53],"by":[54,105,136],"domain":[55,58,102],"adaptation":[56],"randomization":[59],"expose":[61],"an":[62,82],"agent":[63,83,99],"scenarios":[65],"that":[66,116],"fill":[67],"inherent":[69],"gaps":[70],"sim2sim":[72],"sim2real":[74],"approaches.":[75],"However,":[76],"is":[78,152],"inefficient":[79],"train":[81],"environments":[85,175],"randomized":[87],"conditions":[88],"learn":[90,109],"important":[92],"features":[93],"its":[95],"current":[96],"state.":[97],"An":[98],"can":[100],"use":[101],"knowledge":[103],"provided":[104,135],"human":[106,137],"experts":[107,138],"efficiently.":[110],"propose":[112],"novel":[114],"approach":[115],"uses":[117],"graph":[118],"neural":[119],"networks":[120],"conjunction":[122],"deep":[124],"reinforcement":[125],"learning,":[126],"enabling":[127],"decision-making":[128,166],"over":[129],"graphs":[130],"containing":[131],"relevant":[132],"information":[134],"predict":[140],"robot's":[142],"optimal":[143],"sensing":[144],"action":[145],"belief":[147],"space.":[148],"The":[149],"policy,":[150],"trained":[153],"only":[154],"offers":[160],"real-time,":[162],"scalable,":[163],"transferable":[165],"strategy,":[167],"resulting":[168],"zero-shot":[170],"even":[177],"real-world":[178],"environments.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}