{"id":"https://openalex.org/W3187709438","doi":"https://doi.org/10.24963/ijcai.2021/436","title":"Reward-Constrained Behavior Cloning","display_name":"Reward-Constrained Behavior Cloning","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3187709438","doi":"https://doi.org/10.24963/ijcai.2021/436","mag":"3187709438"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/436","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/436","pdf_url":"https://www.ijcai.org/proceedings/2021/0436.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0436.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104504332","display_name":"Zhaorong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaorong Wang","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377147","display_name":"Meng Wang","orcid":"https://orcid.org/0000-0002-3094-7735"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Wang","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021087212","display_name":"Jingqi Zhang","orcid":"https://orcid.org/0000-0003-4140-7029"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqi Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103121632","display_name":"Yingfeng Chen","orcid":"https://orcid.org/0000-0002-9747-5947"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingfeng Chen","raw_affiliation_strings":["NetEase Fuxi AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010176958","display_name":"Chongjie Zhang","orcid":"https://orcid.org/0000-0001-8068-0162"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongjie Zhang","raw_affiliation_strings":["MMW, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMW, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4198,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69346028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3169","last_page":"3175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9711999893188477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8278653621673584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.771037220954895},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.7273311614990234},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6847941279411316},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5760540962219238},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5388931632041931},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5302823185920715},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.49791622161865234},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.4499465227127075},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.41432344913482666},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38274192810058594},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2401968240737915},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09643489122390747},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09316200017929077},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08457517623901367}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8278653621673584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.771037220954895},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.7273311614990234},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6847941279411316},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5760540962219238},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5388931632041931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5302823185920715},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.49791622161865234},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.4499465227127075},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.41432344913482666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38274192810058594},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2401968240737915},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09643489122390747},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09316200017929077},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08457517623901367},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/436","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/436","pdf_url":"https://www.ijcai.org/proceedings/2021/0436.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/436","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/436","pdf_url":"https://www.ijcai.org/proceedings/2021/0436.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187709438.pdf","grobid_xml":"https://content.openalex.org/works/W3187709438.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2098774185","https://openalex.org/W2142641780","https://openalex.org/W2155968351","https://openalex.org/W2156869222","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2342840547","https://openalex.org/W2397581010","https://openalex.org/W2727840223","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2784465508","https://openalex.org/W2803616302","https://openalex.org/W2804791273","https://openalex.org/W2886585480","https://openalex.org/W2911618937","https://openalex.org/W2949561945","https://openalex.org/W2951543502","https://openalex.org/W2962803570","https://openalex.org/W2963082979","https://openalex.org/W2963363446","https://openalex.org/W2963856199","https://openalex.org/W2964340170","https://openalex.org/W2998396902","https://openalex.org/W3162902207","https://openalex.org/W4289699847","https://openalex.org/W4293545785","https://openalex.org/W4294562617"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2665305151"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,99],"learning":[2,96],"(RL)":[3],"has":[4],"demonstrated":[5],"success":[6],"in":[7,56,157],"challenging":[8],"decision-making/control":[9],"tasks.":[10],"However,":[11],"RL":[12],"methods,":[13],"which":[14,93,141],"solve":[15],"tasks":[16],"through":[17],"maximizing":[18],"the":[19,43,48,52,57,61,121,143],"expected":[20,122],"reward,":[21],"may":[22,40],"generate":[23],"undesirable":[24,36],"behaviors":[25,37,110],"due":[26],"to":[27,105,119],"inferior":[28],"local":[29],"convergence":[30],"or":[31,108,151],"incompetent":[32],"reward":[33,45,66,114,145,160],"design.":[34],"These":[35],"of":[38,51,159],"agents":[39],"not":[41],"reduce":[42],"total":[44],"but":[46],"destroy":[47],"user":[49],"experience":[50],"application.":[53],"For":[54],"example,":[55],"autonomous":[58],"driving":[59],"task,":[60],"policy":[62,117],"actuated":[63],"by":[64],"speed":[65],"behaves":[67],"much":[68],"more":[69,135],"sudden":[70],"brakes":[71],"while":[72,147],"human":[73,103],"drivers":[74],"generally":[75],"don\u2019t":[76],"do":[77],"that.":[78],"To":[79],"overcome":[80],"this":[81],"problem,":[82],"we":[83],"present":[84],"a":[85],"novel":[86],"method":[87],"named":[88],"Reward-Constrained":[89],"Behavior":[90],"Cloning":[91],"(RCBC)":[92],"synthesizes":[94],"imitation":[95],"and":[97,111],"constrained":[98],"learning.":[100],"RCBC":[101,132],"leverages":[102],"demonstrations":[104],"induce":[106],"desirable":[107],"human-like":[109],"employs":[112],"lower-bound":[113,144],"constraints":[115,146],"for":[116],"optimization":[118],"maximize":[120],"reward.":[123],"Empirical":[124],"results":[125],"on":[126],"popular":[127],"benchmark":[128],"environments":[129],"show":[130],"that":[131],"learns":[133],"signi\ufb01cantly":[134],"human-desired":[136],"policies":[137],"with":[138],"performance":[139],"guarantees":[140],"meet":[142],"performing":[148],"better":[149],"than":[150],"as":[152,154],"well":[153],"baseline":[155],"methods":[156],"terms":[158],"maximization.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}