{"id":"https://openalex.org/W2417281497","doi":"https://doi.org/10.1109/icit.2016.7475012","title":"An unified approach to inverse reinforcement learning by oppositive demonstrations","display_name":"An unified approach to inverse reinforcement learning by oppositive demonstrations","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2417281497","doi":"https://doi.org/10.1109/icit.2016.7475012","mag":"2417281497"},"language":"en","primary_location":{"id":"doi:10.1109/icit.2016.7475012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit.2016.7475012","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 Industrial Technology (ICIT)","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/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":false,"raw_author_name":"Kao-Shing Hwang","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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/A5112165524","display_name":"Yi-Chia Tseng","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":"Yi-Chia Tseng","raw_affiliation_strings":["Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I142974352"],"apc_list":null,"apc_paid":null,"fwci":0.1941,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45568487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1664","last_page":"1668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9815000295639038,"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/T10524","display_name":"Traffic control and management","score":0.9657999873161316,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8558684587478638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.748879611492157},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6240845918655396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.558434247970581},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5120928287506104},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4418366849422455},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.43067386746406555},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11753427982330322},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1006675660610199}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8558684587478638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.748879611492157},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6240845918655396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.558434247970581},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5120928287506104},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4418366849422455},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.43067386746406555},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11753427982330322},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1006675660610199},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit.2016.7475012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit.2016.7475012","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 Industrial Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1557517019","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2119388568","https://openalex.org/W2134491302","https://openalex.org/W2154633587","https://openalex.org/W6674884181","https://openalex.org/W6677845117"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":{"Reinforcement":[0,43],"Learning":[1,44],"(RL)":[2],"techniques":[3],"use":[4],"a":[5,10,22,149],"reward":[6,32],"function":[7,33],"to":[8,13,29,82,92,98,113,144],"correct":[9],"learning":[11,152],"agent":[12,100],"solve":[14],"sequential":[15],"decision":[16],"making":[17],"problems":[18],"through":[19],"interactions":[20],"with":[21,127],"dynamic":[23],"environment,":[24],"but":[25,146],"it":[26,118],"is":[27,53,80,119,131,140],"hard":[28],"design":[30,38],"the":[31,41,56,84,99,110,114,122],"in":[34],"complex":[35],"problems.":[36],"Its":[37],"difficulties":[39],"promote":[40],"Inverse":[42],"(IRL)":[45],"by":[46,86],"deriving":[47],"from":[48],"an":[49,73],"expert's":[50],"demonstrations.":[51,138],"It":[52,139],"assumed":[54],"that":[55,121,134],"demonstrations":[57,63,79,89,128],"are":[58,66],"meaningful":[59],"and":[60,107],"reproducible.":[61],"However,":[62],"of":[64,76,116,124,129,151],"failure":[65,130],"not":[67,141],"entirely":[68],"useless.":[69],"In":[70],"this":[71],"paper,":[72],"unified":[74],"method":[75],"combining":[77],"oppositive":[78],"proposed":[81],"teach":[83],"robot":[85],"showing":[87],"inappropriate":[88],"or":[90],"trying":[91],"exhibit":[93],"unrelated":[94],"behaviors,":[95],"so":[96],"as":[97],"can":[101],"deliberately":[102],"avoid":[103],"such":[104],"bad":[105],"situations":[106],"speed":[108],"up":[109],"learning.":[111],"According":[112],"result":[115],"simulations,":[117],"obvious":[120],"performance":[123],"algorithm":[125],"combined":[126],"better":[132],"than":[133],"has":[135],"only":[136,142],"good":[137],"convenient":[143],"operate":[145],"also":[147],"save":[148],"lot":[150],"time.":[153]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}