{"id":"https://openalex.org/W2554480306","doi":"https://doi.org/10.1109/fuzz-ieee.2016.7737926","title":"Adaboost-like method for inverse reinforcement learning","display_name":"Adaboost-like method for inverse reinforcement learning","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2554480306","doi":"https://doi.org/10.1109/fuzz-ieee.2016.7737926","mag":"2554480306"},"language":"en","primary_location":{"id":"doi:10.1109/fuzz-ieee.2016.7737926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz-ieee.2016.7737926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","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/A5061189209","display_name":"Kao\u2010Shing Hwang","orcid":"https://orcid.org/0000-0001-9234-4836"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of electrical engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of electrical engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075809603","display_name":"Hsuan-yi Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsuan-yi Chiang","raw_affiliation_strings":["Department of electrical engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of electrical engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001081733","display_name":"Wei\u2010Cheng Jiang","orcid":"https://orcid.org/0000-0003-4432-8801"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wei-Cheng Jiang","raw_affiliation_strings":["Department of electrical engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of electrical engineering, National Sun Yat-sen University, Kaohsiung, Taiwan","institution_ids":["https://openalex.org/I142974352"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061189209"],"corresponding_institution_ids":["https://openalex.org/I142974352"],"apc_list":null,"apc_paid":null,"fwci":0.857,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8452316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"45","issue":null,"first_page":"1922","last_page":"1925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9959999918937683,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.7393546104431152},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7306159734725952},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7064216732978821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6827540993690491},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6597918272018433},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6434587836265564},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.5472488403320312},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4881018102169037},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.41845041513442993},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14444485306739807}],"concepts":[{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.7393546104431152},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7306159734725952},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7064216732978821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827540993690491},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6597918272018433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6434587836265564},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.5472488403320312},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4881018102169037},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.41845041513442993},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14444485306739807}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fuzz-ieee.2016.7737926","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz-ieee.2016.7737926","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2065041047","https://openalex.org/W2069855531","https://openalex.org/W2077671246","https://openalex.org/W2105156548","https://openalex.org/W2108114251","https://openalex.org/W2121863487","https://openalex.org/W2144059919","https://openalex.org/W2157667733","https://openalex.org/W4214717370","https://openalex.org/W6669665587","https://openalex.org/W6676576766"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W1966456942","https://openalex.org/W2130711276","https://openalex.org/W4321463377","https://openalex.org/W3148138296","https://openalex.org/W1528400370","https://openalex.org/W2152445738","https://openalex.org/W2610411144"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,21,38,65],"allows":[2],"agents":[3],"to":[4,10,26,41,78,126,139],"use":[5],"trial":[6],"and":[7,55,74,99,102],"error":[8],"method":[9,70,144],"learn":[11],"intelligent":[12],"behaviors":[13],"which":[14],"like":[15],"human":[16],"beings.":[17],"However,":[18],"when":[19],"the":[20,28,43,48,53,56,80,88,91,95,100,104,142,147],"tasks":[22],"become":[23],"difficult,":[24],"how":[25],"define":[27],"reward":[29,44,81,130],"function":[30,45,82],"is":[31,39,67,137],"an":[32,61,128],"imperative":[33],"issue.":[34],"So,":[35],"inverse":[36,63],"reinforcement":[37,64],"proposed":[40,143],"form":[42,127],"that":[46,141],"imitates":[47],"process":[49],"of":[50],"interaction":[51],"between":[52,97],"expert":[54],"environment.":[57],"In":[58,87],"this":[59],"paper,":[60],"Adaboost-like":[62],"methods":[66],"proposed.":[68],"This":[69],"uses":[71],"Adaboost":[72,114],"classifier":[73],"upper":[75,123],"confidence":[76,121,124],"bounds":[77,125],"generate":[79],"for":[83,110],"a":[84,107,133],"complex":[85],"task.":[86],"imitating":[89],"process,":[90],"agent":[92],"continuously":[93],"compares":[94],"difference":[96,105],"itself":[98],"expert,":[101],"then":[103],"decides":[106],"specific":[108],"weight":[109,117],"each":[111],"state":[112,120],"through":[113],"classifier.":[115],"The":[116],"combines":[118],"with":[119],"by":[122],"approximate":[129],"function.":[131],"Finally,":[132],"simulation,":[134],"maze":[135],"environment":[136],"used":[138],"demonstrate":[140],"can":[145],"decrease":[146],"computation":[148],"time.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}