{"id":"https://openalex.org/W4312550960","doi":"https://doi.org/10.1109/iros47612.2022.9981076","title":"Task Decoupling in Preference-based Reinforcement Learning for Personalized Human-Robot Interaction","display_name":"Task Decoupling in Preference-based Reinforcement Learning for Personalized Human-Robot Interaction","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312550960","doi":"https://doi.org/10.1109/iros47612.2022.9981076"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981076","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101475706","display_name":"Mingjiang Liu","orcid":"https://orcid.org/0009-0000-7763-5336"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingjiang Liu","raw_affiliation_strings":["School of Management and Engineering, Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Management and Engineering, Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["School of Management and Engineering, Nanjing University,Department of Control and Systems Engineering,Nanjing,China","Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Management and Engineering, Nanjing University,Department of Control and Systems Engineering,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101475706"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.8324,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.7476701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"848","last_page":"855"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965999722480774,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8112249970436096},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7807337045669556},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7492402791976929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7166684865951538},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6858654022216797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6407998204231262},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.5679635405540466},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5286914706230164},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5268515348434448},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3646396994590759},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10672876238822937},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.06508246064186096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8112249970436096},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7807337045669556},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7492402791976929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166684865951538},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6858654022216797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6407998204231262},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5679635405540466},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5286914706230164},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5268515348434448},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3646396994590759},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10672876238822937},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.06508246064186096},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981076","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G1283425618","display_name":null,"funder_award_id":"2018AAA0101100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7996831764","display_name":null,"funder_award_id":"62073160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1583953806","https://openalex.org/W2116671302","https://openalex.org/W2145339207","https://openalex.org/W2154023516","https://openalex.org/W2257979135","https://openalex.org/W2736601468","https://openalex.org/W2763110165","https://openalex.org/W2779582454","https://openalex.org/W2785722081","https://openalex.org/W2888056933","https://openalex.org/W2911087563","https://openalex.org/W2922038110","https://openalex.org/W2945169717","https://openalex.org/W2953406320","https://openalex.org/W2964177756","https://openalex.org/W3006334608","https://openalex.org/W3091243689","https://openalex.org/W3091627088","https://openalex.org/W3100470991","https://openalex.org/W3130335129","https://openalex.org/W3134002512","https://openalex.org/W3148246558","https://openalex.org/W3169375224","https://openalex.org/W4214717370","https://openalex.org/W4226146935","https://openalex.org/W4289288058","https://openalex.org/W4321392130","https://openalex.org/W6677285668","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748210908","https://openalex.org/W6753960536","https://openalex.org/W6796168157","https://openalex.org/W6799431981","https://openalex.org/W6810044100","https://openalex.org/W6838843634"],"related_works":["https://openalex.org/W2937325523","https://openalex.org/W4205377104","https://openalex.org/W257970033","https://openalex.org/W1994181006","https://openalex.org/W2911102221","https://openalex.org/W4285602503","https://openalex.org/W4281387587","https://openalex.org/W2943672508","https://openalex.org/W4383737174","https://openalex.org/W4320918405"],"abstract_inverted_index":{"Intelligent":[0],"robots":[1,30,121],"designed":[2],"to":[3,12,14,31,119,122,137,142],"interact":[4],"with":[5,37,144],"hu-mans":[6],"in":[7,65,78,106],"the":[8,15,66,84,94,102,139],"real":[9],"world":[10],"need":[11],"adapt":[13],"preferences":[16,53],"of":[17,86,93],"different":[18],"individuals.":[19],"Preference-based":[20],"reinforcement":[21],"learning":[22,47],"(RL)":[23],"has":[24],"shown":[25],"great":[26],"potential":[27],"for":[28,171],"teaching":[29],"learn":[32],"personalized":[33,172],"behaviors":[34],"from":[35,104,116,132],"interacting":[36],"humans":[38],"with-out":[39],"a":[40,51,111,129,166],"meticulous,":[41],"hand-crafted":[42],"reward":[43,48,69,114,131,156],"function,":[44],"replaced":[45],"by":[46],"based":[49],"on":[50],"human's":[52],"between":[54],"two":[55,150],"robot":[56],"trajectories.":[57],"However,":[58],"poor":[59,63],"feedback":[60],"efficiency":[61],"and":[62,68,168],"exploration":[64],"state":[67],"spaces":[70],"make":[71],"current":[72],"preference-based":[73,87,97,133],"RL":[74,134],"algorithms":[75],"perform":[76],"poorly":[77],"complex":[79],"interactive":[80],"tasks.":[81],"To":[82],"improve":[83],"performance":[85],"RL,":[88],"we":[89,100],"incorporate":[90],"prior":[91],"knowledge":[92],"task":[95,103,113,117,126],"into":[96],"RL.":[98],"Specifically,":[99],"decouple":[101],"preference":[105],"human-robot":[107,173],"interaction.":[108,174],"We":[109],"utilize":[110],"sketchy":[112],"derived":[115],"priori":[118],"instruct":[120],"conduct":[123],"more":[124],"effective":[125,169],"exploration.":[127],"Then":[128],"learned":[130],"is":[135,165,176],"used":[136],"optimize":[138],"robot's":[140],"policy":[141],"align":[143],"human":[145],"preferences.":[146],"In":[147],"addition,":[148],"these":[149],"parts":[151],"are":[152],"combined":[153],"organically":[154],"via":[155],"shaping.":[157],"The":[158],"experimental":[159],"results":[160],"show":[161],"that":[162],"our":[163],"method":[164],"practical":[167],"solution":[170],"Code":[175],"available":[177],"at":[178],"https://github.com/Wenminggong/PbRL_for_PHRI.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}