{"id":"https://openalex.org/W4387092553","doi":"https://doi.org/10.1109/lra.2023.3320009","title":"Reward Learning With Intractable Normalizing Functions","display_name":"Reward Learning With Intractable Normalizing Functions","publication_year":2023,"publication_date":"2023-09-27","ids":{"openalex":"https://openalex.org/W4387092553","doi":"https://doi.org/10.1109/lra.2023.3320009"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3320009","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lra.2023.3320009","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5054965664","display_name":"Joshua Hoegerman","orcid":"https://orcid.org/0000-0002-0701-163X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joshua Hoegerman","raw_affiliation_strings":["Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-0701-163X","affiliations":[{"raw_affiliation_string":"Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063608480","display_name":"Dylan P. Losey","orcid":"https://orcid.org/0000-0002-8787-5293"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan Losey","raw_affiliation_strings":["Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8787-5293","affiliations":[{"raw_affiliation_string":"Collaborative Robotics Lab (Collab), Department of Mechanical Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054965664"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12397917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"11","first_page":"7511","last_page":"7518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9911999702453613,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.98580002784729,"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":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6411950588226318},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6142500638961792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5823193788528442},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4799506962299347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4472202658653259}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6411950588226318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6142500638961792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5823193788528442},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4799506962299347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4472202658653259}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3320009","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/lra.2023.3320009","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1188302780","https://openalex.org/W1964607942","https://openalex.org/W1984048068","https://openalex.org/W1994648061","https://openalex.org/W2105925198","https://openalex.org/W2151516755","https://openalex.org/W2581158580","https://openalex.org/W2889990052","https://openalex.org/W3003858867","https://openalex.org/W3101780148","https://openalex.org/W3103578989","https://openalex.org/W3106171760","https://openalex.org/W3197594072","https://openalex.org/W3205292576","https://openalex.org/W3205824709","https://openalex.org/W3208223622","https://openalex.org/W4212901515","https://openalex.org/W4385181053","https://openalex.org/W6635261211","https://openalex.org/W6638440308","https://openalex.org/W6674884181","https://openalex.org/W6679958247","https://openalex.org/W6696380822","https://openalex.org/W6743368274","https://openalex.org/W6755946096","https://openalex.org/W6774122581"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4379251913","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Robots":[0],"can":[1],"learn":[2],"to":[3,75,109,134],"imitate":[4],"humans":[5],"by":[6],"inferring":[7],"what":[8],"the":[9,24,27,46,52,54,61,63,92,106,124,152,170,177],"human":[10,140],"is":[11,19,42,142],"optimizing":[12],"for.":[13],"One":[14],"common":[15],"framework":[16],"for":[17,121],"this":[18,40,77,80],"Bayesian":[20],"reward":[21,37,115,126,172],"learning,":[22],"where":[23],"robot":[25,47],"treats":[26],"human's":[28,125,153,171],"demonstrations":[29],"and":[30,59,90,95,147,163],"corrections":[31],"as":[32,144],"observations":[33],"of":[34,97],"their":[35,98],"underlying":[36],"function.":[38],"Unfortunately,":[39],"inference":[41],"<italic":[43,111,184,188],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[44,112,185,189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">doubly-intractable:</i>":[45],"must":[48],"reason":[49],"over":[50],"all":[51,60],"trajectories":[53],"person":[55,64],"could":[56,65],"have":[57,66],"provided":[58],"rewards":[62],"in":[67,127],"mind.":[68],"Prior":[69],"work":[70],"uses":[71],"existing":[72],"robotic":[73],"tools":[74],"approximate":[76],"normalizer.":[78],"In":[79],"letter,":[81],"we":[82],"group":[83],"previous":[84,159],"approaches":[85],"into":[86],"three":[87],"fundamental":[88],"classes":[89],"analyze":[91],"theoretical":[93],"pros":[94],"cons":[96],"approach.":[99],"We":[100,130],"then":[101],"leverage":[102],"recent":[103],"research":[104],"from":[105,182],"statistics":[107],"community":[108],"introduce":[110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Double":[113],"MH":[114,133],"learning</i>,":[116],"a":[117],"Monte":[118],"Carlo":[119],"method":[120],"asymptotically":[122],"learning":[123,181],"continuous":[128],"spaces.":[129],"extend":[131],"Double":[132],"conditionally":[135,148],"independent":[136],"settings":[137],"(where":[138,151],"each":[139],"correction":[141,155],"viewed":[143],"completely":[145],"separate)":[146],"dependent":[149],"environments":[150],"current":[154],"may":[156],"build":[157],"on":[158],"inputs).":[160],"Across":[161],"simulations":[162],"user":[164],"studies,":[165],"our":[166],"proposed":[167],"approach":[168],"infers":[169],"parameters":[173],"more":[174],"accurately":[175],"than":[176],"alternate":[178],"approximations":[179],"when":[180],"either":[183],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">demonstrations</i>":[186],"or":[187],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">corrections</i>.":[190]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}