{"id":"https://openalex.org/W4214890001","doi":"https://doi.org/10.1109/icaiic54071.2022.9722629","title":"Merging Reinforcement Learning and Inverse Reinforcement Learning via Auxiliary Reward System","display_name":"Merging Reinforcement Learning and Inverse Reinforcement Learning via Auxiliary Reward System","publication_year":2022,"publication_date":"2022-02-21","ids":{"openalex":"https://openalex.org/W4214890001","doi":"https://doi.org/10.1109/icaiic54071.2022.9722629"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic54071.2022.9722629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic54071.2022.9722629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5010390965","display_name":"Wadhah Zeyad Tareq Tareq","orcid":"https://orcid.org/0000-0003-4571-0295"},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Wadhah Zeyad Tareq","raw_affiliation_strings":["Yıldız Technical University,Computer Engineering,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Yıldız Technical University,Computer Engineering,Istanbul,Turkey","institution_ids":["https://openalex.org/I4101805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080453744","display_name":"Mehmet Fatih Amasyal\u0131","orcid":"https://orcid.org/0000-0002-0404-5973"},"institutions":[{"id":"https://openalex.org/I4101805","display_name":"Y\u0131ld\u0131z Technical University","ror":"https://ror.org/0547yzj13","country_code":"TR","type":"education","lineage":["https://openalex.org/I4101805"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mehmet Fatih Amasyali","raw_affiliation_strings":["Yıldız Technical University,Computer Engineering,Istanbul,Turkey"],"affiliations":[{"raw_affiliation_string":"Yıldız Technical University,Computer Engineering,Istanbul,Turkey","institution_ids":["https://openalex.org/I4101805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010390965"],"corresponding_institution_ids":["https://openalex.org/I4101805"],"apc_list":null,"apc_paid":null,"fwci":0.6628,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72892517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"292","last_page":"297"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8233898282051086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353876829147339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6541703939437866},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5286327600479126},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5169733762741089},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.514914870262146},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4298958480358124},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39836692810058594},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3981459140777588},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3014642596244812},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10105609893798828}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8233898282051086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353876829147339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6541703939437866},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5286327600479126},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5169733762741089},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.514914870262146},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4298958480358124},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39836692810058594},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3981459140777588},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3014642596244812},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10105609893798828},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic54071.2022.9722629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic54071.2022.9722629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":41,"referenced_works":["https://openalex.org/W1591675293","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2201581102","https://openalex.org/W2270835334","https://openalex.org/W2347074400","https://openalex.org/W2724169821","https://openalex.org/W2746553466","https://openalex.org/W2751530711","https://openalex.org/W2761873684","https://openalex.org/W2788862220","https://openalex.org/W2805560727","https://openalex.org/W2898191412","https://openalex.org/W2914261249","https://openalex.org/W2951799221","https://openalex.org/W2963508354","https://openalex.org/W2964043796","https://openalex.org/W3011120880","https://openalex.org/W3202607075","https://openalex.org/W4298876402","https://openalex.org/W4300198501","https://openalex.org/W6635261211","https://openalex.org/W6674884181","https://openalex.org/W6677067356","https://openalex.org/W6683300800","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6694257392","https://openalex.org/W6740092555","https://openalex.org/W6744838376","https://openalex.org/W6745347688","https://openalex.org/W6748645729","https://openalex.org/W6751714826","https://openalex.org/W6751955673","https://openalex.org/W6755724153","https://openalex.org/W6758978475","https://openalex.org/W6775686901","https://openalex.org/W6802252023"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2107890255","https://openalex.org/W2089013912","https://openalex.org/W2106552856","https://openalex.org/W2076061571","https://openalex.org/W2038908348","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"In":[0,81,106,144],"recent":[1],"years,":[2],"learning":[3,46,172],"from":[4,19,47,122,156],"demonstration":[5,20,158],"has":[6],"become":[7],"one":[8],"of":[9,66,136,187],"the":[10,50,53,57,60,64,67,78,109,134,140,153,157,164,174,179,182,185,188],"promising":[11],"methods":[12],"in":[13,56,90,139],"robotics":[14],"and":[15,59,159],"interactive":[16],"systems.":[17],"Learning":[18,113,149],"is":[21,49,70,84,96],"a":[22,37],"model":[23],"by":[24,29],"which":[25],"an":[26,31,91,129],"agent":[27,39,110,125,175,189],"learns":[28],"observing":[30],"expert.":[32],"The":[33,42,124,167],"expert":[34],"could":[35],"be":[36],"pre-trained":[38],"or":[40],"human.":[41],"main":[43],"problem":[44,135],"with":[45,128,178],"demonstrations":[48,58],"difference":[51],"between":[52],"reward":[54,131],"representation":[55],"actual":[61,92],"environment.":[62,93],"During":[63],"construction":[65],"demonstrations,":[68],"it":[69,83],"easy":[71,86],"to":[72,76,87,102,115,118,132,151,176],"add":[73],"new":[74],"rewards":[75,138,155],"enhancement":[77],"agent\u2019s":[79],"performance.":[80],"contrast,":[82],"not":[85],"do":[88],"that":[89,170],"This":[94],"work":[95,101],"built":[97],"upon":[98],"our":[99],"previous":[100,107],"solve":[103,133],"this":[104,145],"problem.":[105],"work,":[108,146],"uses":[111,150],"Reinforcement":[112,148],"algorithms":[114],"learn":[116],"how":[117],"play":[119],"video":[120],"games":[121],"demonstrations.":[123],"was":[126],"supplied":[127],"external":[130,154],"missing":[137],"hard":[141],"exploration":[142],"environments.":[143],"Inverse":[147],"extract":[152],"make":[160],"them":[161],"available":[162],"during":[163],"interaction":[165],"period.":[166],"results":[168],"showed":[169],"inverse":[171],"enables":[173],"interact":[177],"environment":[180],"after":[181],"pre-training.":[183],"Furthermore,":[184],"performance":[186],"becomes":[190],"more":[191],"stable.":[192]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}