{"id":"https://openalex.org/W4388675145","doi":"https://doi.org/10.1109/allerton58177.2023.10313475","title":"Inverse Reinforcement Learning with Learning and Leveraging Demonstrators\u2019 Varying Expertise Levels","display_name":"Inverse Reinforcement Learning with Learning and Leveraging Demonstrators\u2019 Varying Expertise Levels","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4388675145","doi":"https://doi.org/10.1109/allerton58177.2023.10313475"},"language":"en","primary_location":{"id":"doi:10.1109/allerton58177.2023.10313475","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton58177.2023.10313475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","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/A5093262528","display_name":"Somtochukwu Oguchienti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Somtochukwu Oguchienti","raw_affiliation_strings":["Purdue University,School of Electrical and Computer Engineering,Indiana,USA","School of Electrical and Computer Engineering, Purdue University, Indiana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,Indiana,USA","institution_ids":[]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, Indiana, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101793459","display_name":"Mahsa Ghasemi","orcid":"https://orcid.org/0000-0003-4302-4806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahsa Ghasemi","raw_affiliation_strings":["Purdue University,School of Electrical and Computer Engineering,Indiana,USA","School of Electrical and Computer Engineering, Purdue University, Indiana, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,School of Electrical and Computer Engineering,Indiana,USA","institution_ids":[]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Purdue University, Indiana, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9858999848365784,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/leverage","display_name":"Leverage (statistics)","score":0.8014203310012817},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7832359075546265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7046442031860352},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5683252811431885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5608434677124023},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5078597664833069},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4910154342651367},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4332123100757599},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17188197374343872},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09069794416427612}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8014203310012817},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7832359075546265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046442031860352},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5683252811431885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608434677124023},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5078597664833069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4910154342651367},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4332123100757599},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17188197374343872},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09069794416427612},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton58177.2023.10313475","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/allerton58177.2023.10313475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W121023703","https://openalex.org/W1583953806","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2116157560","https://openalex.org/W2117675763","https://openalex.org/W2137375617","https://openalex.org/W2156869222","https://openalex.org/W2165664253","https://openalex.org/W2486334580","https://openalex.org/W2567252694","https://openalex.org/W2612346912","https://openalex.org/W2735318784","https://openalex.org/W2914931737","https://openalex.org/W2938421504","https://openalex.org/W2962937519","https://openalex.org/W2963508354","https://openalex.org/W2963802910","https://openalex.org/W2964177756","https://openalex.org/W3022566517","https://openalex.org/W3093784762","https://openalex.org/W3174132892","https://openalex.org/W3209866168","https://openalex.org/W4210809301","https://openalex.org/W4211049957","https://openalex.org/W4226373607","https://openalex.org/W4288284400","https://openalex.org/W4289288058","https://openalex.org/W4289419964","https://openalex.org/W4300110528","https://openalex.org/W4300198501","https://openalex.org/W4313598235","https://openalex.org/W4321392130","https://openalex.org/W6604963999","https://openalex.org/W6674884181","https://openalex.org/W6677262939","https://openalex.org/W6677555207","https://openalex.org/W6680322746","https://openalex.org/W6684578268","https://openalex.org/W6732417791","https://openalex.org/W6739585900","https://openalex.org/W6745347688","https://openalex.org/W6751955673","https://openalex.org/W6753960536","https://openalex.org/W6761908843","https://openalex.org/W6766375498","https://openalex.org/W6769174716","https://openalex.org/W6776438516","https://openalex.org/W6780559895","https://openalex.org/W6785034342","https://openalex.org/W6802868314","https://openalex.org/W6810476337","https://openalex.org/W6848774067"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W2768698792"],"abstract_inverted_index":{"A":[0],"common":[1],"assumption":[2,22],"in":[3,26,212],"most":[4],"Inverse":[5,107],"Reinforcement":[6,108],"Learning":[7,109],"(IRL)":[8],"methods":[9,251],"is":[10,82],"that":[11,164,202,229,252],"human":[12,45],"demonstrations":[13,58,117,141,196,243],"are":[14,93],"drawn":[15],"from":[16,59,110,118,132,183,193],"an":[17,147,187],"optimal":[18,139],"policy.":[19],"However,":[20],"this":[21,72,75],"poses":[23],"a":[24,53,103,128,161,166,198,246],"problem":[25,149],"real-world":[27],"applications,":[28],"as":[29,52],"humans":[30,60,92],"may":[31],"have":[32,49,66],"varying":[33],"aptitudes":[34],"for":[35,256],"different":[36,62,119,122],"tasks.":[37],"To":[38,171],"address":[39],"this,":[40],"preference-based":[41],"IRL":[42],"methods,":[43],"using":[44],"rankings":[46],"of":[47,64,86,124,137,175],"trajectories,":[48],"been":[50,68],"explored":[51],"potential":[54],"solution.":[55],"More":[56],"recently,":[57],"with":[61,121],"levels":[63,90,123,240],"expertise":[65,89,125,239,258],"also":[67],"utilized":[69],"to":[70,97,126,150,158,244],"relax":[71],"assumption.":[73],"In":[74,143],"paper,":[76],"we":[77,101,145,178],"consider":[78],"scenarios":[79],"where":[80],"there":[81],"no":[83],"prior":[84],"knowledge":[85],"the":[87,173,204,209,217,222,230,238,242,250,257],"demonstrators\u2019":[88],"and":[91,154,197,221,236],"not":[94,254],"readily":[95],"available":[96],"provide":[98],"rankings.":[99],"Therefore,":[100],"propose":[102],"new":[104],"method":[105,232],"called":[106],"Varying":[111],"Expertise":[112],"Levels":[113],"(IRL-VEL),":[114],"which":[115],"combines":[116],"demonstrators":[120],"learn":[127,151,160,179,235,245],"high":[129],"performance":[130,174],"policy":[131,167],"their":[133,140],"proficiency":[134,205],"scores\u2014an":[135],"indication":[136],"how":[138],"are.":[142],"particular,":[144],"solve":[146],"optimization":[148],"these":[152,194],"scores":[153],"subsequently":[155],"use":[156],"them":[157],"efficiently":[159],"reward":[162,185,189,200],"function":[163,190,201],"optimizes":[165],"through":[168],"reinforcement":[169],"learning.":[170],"assess":[172],"our":[176],"algorithm,":[177],"two":[180,184,213],"separate":[181],"policies":[182],"functions:":[186],"initial":[188],"directly":[191],"obtained":[192],"combined":[195],"final":[199],"incorporates":[203],"scores.":[206],"We":[207],"evaluate":[208],"proposed":[210,231],"algorithm":[211],"simulation":[214,226],"environments,":[215],"namely,":[216],"continuous":[218],"mountain":[219],"car":[220],"MuJoCo":[223],"swimmer.":[224],"The":[225],"results":[227],"demonstrate":[228],"can":[233],"effectively":[234],"leverage":[237],"underlying":[241],"policy,":[247],"significantly":[248],"outperforming":[249],"do":[253],"account":[255],"levels.":[259]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}