{"id":"https://openalex.org/W3212285017","doi":"https://doi.org/10.1109/iecon48115.2021.9589967","title":"Inferring Cost Functions Using Reward Parameter Search and Policy Gradient Reinforcement Learning","display_name":"Inferring Cost Functions Using Reward Parameter Search and Policy Gradient Reinforcement Learning","publication_year":2021,"publication_date":"2021-10-13","ids":{"openalex":"https://openalex.org/W3212285017","doi":"https://doi.org/10.1109/iecon48115.2021.9589967","mag":"3212285017"},"language":"en","primary_location":{"id":"doi:10.1109/iecon48115.2021.9589967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon48115.2021.9589967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2021 \u2013 47th Annual Conference of the IEEE Industrial Electronics Society","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/A5091283970","display_name":"Emir Arditi","orcid":"https://orcid.org/0000-0002-6429-5042"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Emir Arditi","raw_affiliation_strings":["Ozyegin University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033357188","display_name":"Tja\u0161a Kunavar","orcid":"https://orcid.org/0000-0003-3403-3241"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Tjasa Kunavar","raw_affiliation_strings":["Jozef Stefan Institute, Ljubljana, Slovenia"],"affiliations":[{"raw_affiliation_string":"Jozef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048165304","display_name":"Emre U\u011fur","orcid":"https://orcid.org/0000-0001-9597-2731"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Emre Ugur","raw_affiliation_strings":["Bogazici University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Bogazici University, Istanbul, Turkey","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060743876","display_name":"Jan Babi\u010d","orcid":"https://orcid.org/0000-0002-1870-8264"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Jan Babic","raw_affiliation_strings":["Jozef Stefan Institute, Ljubljana, Slovenia"],"affiliations":[{"raw_affiliation_string":"Jozef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018729334","display_name":"Erhan \u00d6ztop","orcid":"https://orcid.org/0000-0002-3051-6038"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"Osaka University","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]},{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["JP","TR"],"is_corresponding":false,"raw_author_name":"Erhan Oztop","raw_affiliation_strings":["Osaka University, Osaka, Japan","Ozyegin University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091283970"],"corresponding_institution_ids":["https://openalex.org/I44925452"],"apc_list":null,"apc_paid":null,"fwci":0.0846,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40108244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T10784","display_name":"Muscle activation and electromyography studies","score":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9954000115394592,"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/T10982","display_name":"Motor Control and Adaptation","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/squat","display_name":"Squat","score":0.8484275341033936},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7902930378913879},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5872359275817871},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5547253489494324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5098587870597839},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5022175312042236},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4542534649372101},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.44687068462371826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4418472945690155},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43513602018356323},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3419747054576874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2800465226173401},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15180012583732605},{"id":"https://openalex.org/keywords/physical-medicine-and-rehabilitation","display_name":"Physical medicine and rehabilitation","score":0.09849843382835388}],"concepts":[{"id":"https://openalex.org/C2778820510","wikidata":"https://www.wikidata.org/wiki/Q1755746","display_name":"Squat","level":2,"score":0.8484275341033936},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7902930378913879},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5872359275817871},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5547253489494324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098587870597839},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5022175312042236},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4542534649372101},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.44687068462371826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4418472945690155},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43513602018356323},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3419747054576874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2800465226173401},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15180012583732605},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.09849843382835388},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iecon48115.2021.9589967","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon48115.2021.9589967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2021 \u2013 47th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/8149","is_oa":false,"landing_page_url":"http://hdl.handle.net/10679/8149","pdf_url":null,"source":{"id":"https://openalex.org/S4306400232","display_name":"ECS Journal of Solid State Science and Technology (The Electrochemical Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802273670","host_organization_name":"Electrochemical Society","host_organization_lineage":["https://openalex.org/I2802273670"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1801976851","https://openalex.org/W1929981607","https://openalex.org/W2002079422","https://openalex.org/W2098774185","https://openalex.org/W2121103318","https://openalex.org/W2145339207","https://openalex.org/W2290104316","https://openalex.org/W2290354866","https://openalex.org/W2462015191","https://openalex.org/W2509431599","https://openalex.org/W2736601468","https://openalex.org/W2751530711","https://openalex.org/W2950471160","https://openalex.org/W2963277051","https://openalex.org/W2963590100","https://openalex.org/W2963864421","https://openalex.org/W2966552064","https://openalex.org/W6638440308","https://openalex.org/W6640443443","https://openalex.org/W6674884181","https://openalex.org/W6678367057","https://openalex.org/W6684921986","https://openalex.org/W6696324988","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6741002519"],"related_works":["https://openalex.org/W2035481409","https://openalex.org/W2989749062","https://openalex.org/W1545335609","https://openalex.org/W3147031369","https://openalex.org/W1968508013","https://openalex.org/W1942947904","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"This":[0],"study":[1],"focuses":[2],"on":[3,85],"inferring":[4],"cost":[5,48],"functions":[6],"of":[7,33,36,53,87,104,128,141],"obtained":[8,29,125],"movement":[9],"data":[10,24],"using":[11],"reward":[12,138],"parameter":[13,44],"search":[14],"and":[15,111,117],"pol-icy":[16],"gradient":[17,74],"based":[18,84],"Reinforcement":[19,121],"Learning":[20],"(RL).":[21],"The":[22,42,98,130],"behavior":[23],"for":[25,134],"this":[26],"task":[27],"is":[28,50,65,89,106,124],"through":[30],"a":[31,72,113,115,118],"series":[32],"squat-to-stand":[34,60,69],"movements":[35,70],"human":[37],"participants":[38],"under":[39],"dynamic":[40],"perturbations.":[41],"key":[43],"searched":[45],"in":[46,57,100,126],"the":[47,51,59,93,101,137,142],"function":[49,139],"weight":[52,96],"total":[54],"torque":[55],"used":[56,66,90],"performing":[58],"action.":[61],"An":[62],"approximate":[63],"model":[64],"to":[67,91],"learn":[68],"via":[71],"policy":[73],"method,":[75],"namely":[76],"Proximal":[77],"Policy":[78],"Optimization(PPO).":[79],"A":[80],"behavioral":[81],"similarity":[82],"metric":[83],"Center":[86],"Mass(COM)":[88],"find":[92],"most":[94],"likely":[95],"parameter.":[97],"stochasticity":[99],"training":[102],"result":[103],"PPO":[105],"dealt":[107],"with":[108],"multiple":[109],"runs,":[110],"as":[112],"result,":[114],"reasonable":[116],"stable":[119],"Inverse":[120],"Learning(IRL)":[122],"algorithm":[123],"terms":[127],"performance.":[129],"results":[131],"indicate":[132],"that":[133],"some":[135],"participants,":[136],"parameters":[140],"experts":[143],"were":[144],"inferred":[145],"successfully.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}