{"id":"https://openalex.org/W2211613407","doi":"https://doi.org/10.1109/iros.2015.7354121","title":"Apprenticeship learning based on inconsistent demonstrations","display_name":"Apprenticeship learning based on inconsistent demonstrations","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2211613407","doi":"https://doi.org/10.1109/iros.2015.7354121","mag":"2211613407"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2015.7354121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5046607392","display_name":"Gakuto Masuyama","orcid":"https://orcid.org/0000-0002-4776-4863"},"institutions":[{"id":"https://openalex.org/I96679780","display_name":"Chuo University","ror":"https://ror.org/03qvqb743","country_code":"JP","type":"education","lineage":["https://openalex.org/I96679780"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gakuto Masuyama","raw_affiliation_strings":["Department of Precision Mechanics, Chuo University, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Precision Mechanics, Chuo University, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I96679780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083854260","display_name":"Kazunori Umeda","orcid":"https://orcid.org/0000-0002-4458-4648"},"institutions":[{"id":"https://openalex.org/I96679780","display_name":"Chuo University","ror":"https://ror.org/03qvqb743","country_code":"JP","type":"education","lineage":["https://openalex.org/I96679780"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Umeda","raw_affiliation_strings":["Department of Precision Mechanics, Chuo University, Bunkyo-ku, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Precision Mechanics, Chuo University, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I96679780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046607392"],"corresponding_institution_ids":["https://openalex.org/I96679780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06829732,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"5273","last_page":"5278"},"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":0.993399977684021,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9898999929428101,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6666366457939148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.652918815612793},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.636311411857605},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6244648694992065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6130994558334351},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5547126531600952},{"id":"https://openalex.org/keywords/apprenticeship","display_name":"Apprenticeship","score":0.5304913520812988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5238202214241028},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4406867027282715},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4314723610877991},{"id":"https://openalex.org/keywords/inverse-dynamics","display_name":"Inverse dynamics","score":0.4302450716495514},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4119746685028076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19544824957847595}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6666366457939148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.652918815612793},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.636311411857605},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6244648694992065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6130994558334351},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5547126531600952},{"id":"https://openalex.org/C107806365","wikidata":"https://www.wikidata.org/wiki/Q253567","display_name":"Apprenticeship","level":2,"score":0.5304913520812988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5238202214241028},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4406867027282715},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4314723610877991},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.4302450716495514},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4119746685028076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19544824957847595},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2015.7354121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":21,"referenced_works":["https://openalex.org/W1591675293","https://openalex.org/W1925816294","https://openalex.org/W1977655452","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2062289172","https://openalex.org/W2101786389","https://openalex.org/W2103851188","https://openalex.org/W2119914747","https://openalex.org/W2121863487","https://openalex.org/W2128575093","https://openalex.org/W2133068870","https://openalex.org/W2169498096","https://openalex.org/W2172968643","https://openalex.org/W3005581722","https://openalex.org/W4214717370","https://openalex.org/W6635261211","https://openalex.org/W6640290305","https://openalex.org/W6675410418","https://openalex.org/W6677978604","https://openalex.org/W6679958247"],"related_works":["https://openalex.org/W2130264791","https://openalex.org/W4235622043","https://openalex.org/W2155887593","https://openalex.org/W2102428166","https://openalex.org/W1600547024","https://openalex.org/W3125491562","https://openalex.org/W2239395319","https://openalex.org/W2573907782","https://openalex.org/W2687915465","https://openalex.org/W3142528978"],"abstract_inverted_index":{"Apprenticeship":[0],"learning":[1,111],"based":[2,102],"on":[3,103],"inconsistent":[4,77],"demonstrations":[5,17,78],"is":[6,52,96,119],"presented":[7],"in":[8,123],"this":[9],"paper.":[10],"We":[11],"address":[12],"a":[13,40,43,55,136],"problem":[14],"where":[15],"given":[16],"are":[18,79,112],"not":[19],"directly":[20],"applicable":[21],"to":[22,27,53],"reward":[23],"function":[24],"estimation":[25],"due":[26],"the":[28,34,37,49,58,62,88,90,99,105],"non-stationarity":[29],"of":[30,39,48,57,92,116,130,135],"an":[31,82,131],"environment":[32,132],"or":[33],"difference":[35],"between":[36],"dynamics":[38],"robot":[41],"and":[42,76,133],"demonstrator.":[44],"A":[45],"basic":[46],"idea":[47],"proposed":[50],"method":[51],"use":[54],"subset":[56],"trajectories":[59,75,101],"sampled":[60],"from":[61],"baseline":[63],"policy":[64],"as":[65],"training":[66,106],"data":[67,107],"for":[68,108],"inverse":[69,109],"reinforcement":[70,110],"learning.":[71],"All":[72],"consistent":[73],"sample":[74,94,100],"abstracted":[80],"by":[81,128],"affine":[83],"transformation":[84],"invariant":[85],"feature.":[86],"Using":[87],"feature,":[89],"importance":[91],"each":[93],"trajectory":[95],"estimated.":[97],"Rating":[98],"importance,":[104],"identified.":[113],"The":[114],"validity":[115],"our":[117],"approach":[118],"verified":[120],"through":[121],"simulation":[122],"two":[124],"scenarios:":[125],"inconsistency":[126],"caused":[127],"variation":[129],"performance":[134],"robot.":[137]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}