{"id":"https://openalex.org/W4383108416","doi":"https://doi.org/10.1109/icra48891.2023.10160473","title":"A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations","display_name":"A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108416","doi":"https://doi.org/10.1109/icra48891.2023.10160473"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"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/A5026114446","display_name":"Sohan Rudra","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sohan Rudra","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006057270","display_name":"Saksham Goel","orcid":"https://orcid.org/0000-0002-8826-7070"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saksham Goel","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012951358","display_name":"Anirban Santara","orcid":"https://orcid.org/0000-0002-1571-3885"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirban Santara","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025258","display_name":"Claudio Gentile","orcid":"https://orcid.org/0000-0003-1551-2167"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Claudio Gentile","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032519970","display_name":"Laurent Perron","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laurent Perron","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676785","display_name":"Fei Xia","orcid":"https://orcid.org/0000-0003-4343-1444"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Xia","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058073838","display_name":"Vikas Sindhwani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikas Sindhwani","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090570382","display_name":"Carolina Parada","orcid":"https://orcid.org/0009-0000-7772-4646"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carolina Parada","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112230947","display_name":"Gaurav Aggarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Aggarwal","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5026114446"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.4939,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64446772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5645","last_page":"5652"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.7726587057113647},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6430760622024536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6033298969268799},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.552464485168457},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5368891358375549},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5336307883262634},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4625418186187744},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4347783625125885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4245494604110718},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.358812153339386},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3450169265270233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726587057113647},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6430760622024536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6033298969268799},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.552464485168457},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5368891358375549},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5336307883262634},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4625418186187744},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4347783625125885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4245494604110718},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.358812153339386},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3450169265270233},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W80909727","https://openalex.org/W1531274257","https://openalex.org/W1543703002","https://openalex.org/W1597685670","https://openalex.org/W1966793805","https://openalex.org/W1969925267","https://openalex.org/W2012715465","https://openalex.org/W2029143333","https://openalex.org/W2031458380","https://openalex.org/W2050883740","https://openalex.org/W2054630393","https://openalex.org/W2059007332","https://openalex.org/W2069830673","https://openalex.org/W2073787051","https://openalex.org/W2078610911","https://openalex.org/W2112420033","https://openalex.org/W2115556222","https://openalex.org/W2116773335","https://openalex.org/W2119738618","https://openalex.org/W2122455045","https://openalex.org/W2125409550","https://openalex.org/W2129160848","https://openalex.org/W2131664039","https://openalex.org/W2133145258","https://openalex.org/W2150839555","https://openalex.org/W2159895118","https://openalex.org/W2168881041","https://openalex.org/W2414919120","https://openalex.org/W2563408008","https://openalex.org/W2732547613","https://openalex.org/W2884565639","https://openalex.org/W2950628579","https://openalex.org/W2950697717","https://openalex.org/W2953127211","https://openalex.org/W2963121255","https://openalex.org/W2963800628","https://openalex.org/W2964339842","https://openalex.org/W2967853831","https://openalex.org/W3007527937","https://openalex.org/W3009928773","https://openalex.org/W3011144238","https://openalex.org/W3034511923","https://openalex.org/W3034728521","https://openalex.org/W3036497058","https://openalex.org/W3040041096","https://openalex.org/W3152331843","https://openalex.org/W3206072662","https://openalex.org/W3210309464","https://openalex.org/W4214717370","https://openalex.org/W4224912544","https://openalex.org/W4287111299","https://openalex.org/W4287704118","https://openalex.org/W4293566037","https://openalex.org/W4298342613","https://openalex.org/W4303697778","https://openalex.org/W4313180266","https://openalex.org/W4385245566","https://openalex.org/W6684102146","https://openalex.org/W6739778489","https://openalex.org/W6739901393","https://openalex.org/W6746518932","https://openalex.org/W6747106673","https://openalex.org/W6753516098","https://openalex.org/W6758824984","https://openalex.org/W6773810110","https://openalex.org/W6774815639","https://openalex.org/W6778299498","https://openalex.org/W6779558354","https://openalex.org/W6780167394","https://openalex.org/W6780443396","https://openalex.org/W6781054291","https://openalex.org/W6798225807","https://openalex.org/W6802517928","https://openalex.org/W6810640255"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W1570928019","https://openalex.org/W2124102101","https://openalex.org/W4250820896","https://openalex.org/W2333383158","https://openalex.org/W4250305970","https://openalex.org/W2903025760"],"abstract_inverted_index":{"Object-goal":[0],"navigation":[1],"(Object-nav)":[2],"entails":[3],"searching,":[4],"recognizing":[5],"and":[6,88,130,139],"navigating":[7],"to":[8,27,45,70,115,134],"a":[9,37,90,110,117,131],"target":[10],"object.":[11],"Object-nav":[12],"has":[13],"been":[14],"extensively":[15],"studied":[16],"by":[17,80],"the":[18,78,84,93,120],"Embodied-AI":[19],"community,":[20],"but":[21,55],"most":[22],"solutions":[23],"are":[24,105],"often":[25],"restricted":[26],"considering":[28],"static":[29,53],"objects":[30,54,58,98],"(e.g.,":[31],"television,":[32],"fridge,":[33],"etc.),":[34],"We":[35,122],"propose":[36],"modular":[38],"framework":[39],"for":[40,50,119],"object-nav":[41],"that":[42,64],"is":[43],"able":[44],"efficiently":[46,76],"search":[47],"indoor":[48],"environments":[49,129],"not":[51],"just":[52],"also":[56],"movable":[57],"(e.g.":[59],"fruits,":[60],"glasses,":[61],"phones,":[62],"etc.)":[63],"frequently":[65],"change":[66],"their":[67],"positions":[68],"due":[69],"human":[71],"intervention.":[72],"Our":[73],"contextual-bandit":[74],"agent":[75],"explores":[77],"environment":[79],"showing":[81],"optimism":[82],"in":[83,109,126],"face":[85],"of":[86,92,95],"uncertainty":[87],"learns":[89],"model":[91],"likelihood":[94],"spotting":[96],"different":[97],"from":[99],"each":[100],"navigable":[101],"location.":[102],"The":[103],"likelihoods":[104],"used":[106],"as":[107],"rewards":[108],"weighted":[111],"minimum":[112],"latency":[113],"solver":[114],"deduce":[116],"trajectory":[118],"robot.":[121],"evaluate":[123],"our":[124],"algorithms":[125],"two":[127],"simulated":[128],"real-world":[132],"setting,":[133],"demonstrate":[135],"high":[136],"sample":[137],"efficiency":[138],"reliability.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}