{"id":"https://openalex.org/W4403487645","doi":"https://doi.org/10.3233/faia240754","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","display_name":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487645","doi":"https://doi.org/10.3233/faia240754"},"language":"en","primary_location":{"id":"doi:10.3233/faia240754","doi":"https://doi.org/10.3233/faia240754","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240754","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W4403488923","display_name":"ECAI 2024"},"type":"book-chapter","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240754","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100672364","display_name":"Shirong Liu","orcid":"https://orcid.org/0000-0002-8357-3116","observed_orcids":["https://orcid.org/0000-0002-8357-3116"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shirong Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044788927","display_name":"Chenjia Bai","orcid":"https://orcid.org/0000-0002-8379-9385","observed_orcids":["https://orcid.org/0000-0002-8379-9385"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenjia Bai","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873331","display_name":"Zixian Guo","orcid":"https://orcid.org/0009-0001-0689-7096","observed_orcids":["https://orcid.org/0009-0001-0689-7096"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixian Guo","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705959","display_name":"Gaurav Sharma A","orcid":"https://orcid.org/0000-0001-9735-9519","observed_orcids":["https://orcid.org/0000-0001-9735-9519"]},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Sharma","raw_affiliation_strings":["University of Rochester, Rochester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602248","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-7240-1546","observed_orcids":["https://orcid.org/0000-0002-7240-1546"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.40923218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/offline-reinforcement-learning","display_name":"offline reinforcement learning","score":0.8679999709129333},{"id":"https://openalex.org/keywords/exponentially-weighted-moving-average","display_name":"exponential moving average","score":0.7409999966621399},{"id":"https://openalex.org/keywords/policy-collapse","display_name":"policy collapse","score":0.609000027179718},{"id":"https://openalex.org/keywords/conservative-policy","display_name":"conservative policy","score":0.7850000262260437},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.6100000143051147}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7087728977203369},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5373470187187195},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5303564667701721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4291419982910156},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3522716462612152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3440113961696625},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.15937486290931702},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/faia240754","doi":"https://doi.org/10.3233/faia240754","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240754","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2408.02165","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.02165","pdf_url":"https://arxiv.org/pdf/2408.02165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2408.02165","doi":"https://doi.org/10.48550/arxiv.2408.02165","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2408.02165","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.3233/faia240754","doi":"https://doi.org/10.3233/faia240754","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240754","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5499399499","display_name":"\u9762\u5411\u836f\u7269\u53d1\u73b0\u7684\u591a\u5173\u7cfb\u53cc\u5c42\u6b21\u751f\u6210\u5f0f\u56fe\u5d4c\u5165\u7814\u7a76","funder_award_id":"62071154","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7108700631","display_name":null,"funder_award_id":"62306242","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403487645.pdf","grobid_xml":"https://content.openalex.org/works/W4403487645.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6947859355","https://openalex.org/W7127133309","https://openalex.org/W7078299334","https://openalex.org/W4307010452","https://openalex.org/W4281661031","https://openalex.org/W4389453968","https://openalex.org/W7162248656","https://openalex.org/W4382318909","https://openalex.org/W4380551983","https://openalex.org/W4310510895"],"abstract_inverted_index":{"Policy":[0],"constraint":[1,65,140],"methods":[2,25],"in":[3,29,104,115],"offline":[4,21,106],"reinforcement":[5],"learning":[6,96],"employ":[7],"additional":[8],"regularization":[9],"techniques":[10],"to":[11,27,49],"constrain":[12],"the":[13,16,20,35,50,68,72,76,95,105,125,138],"discrepancy":[14],"between":[15],"learned":[17,69,82],"policy":[18,64,70,102,139],"and":[19,46],"dataset.":[22],"However,":[23],"these":[24],"tend":[26],"result":[28],"overly":[30],"conservative":[31],"policies":[32,99],"that":[33,66,111,130],"resemble":[34],"behavior":[36],"policy,":[37],"thus":[38],"limiting":[39],"their":[40],"performance.":[41],"We":[42],"investigate":[43],"this":[44,57,86],"limitation":[45],"attribute":[47],"it":[48],"static":[51],"nature":[52],"of":[53,80,97],"traditional":[54],"constraints.":[55],"In":[56],"paper,":[58],"we":[59],"propose":[60],"a":[61,116],"novel":[62],"dynamic":[63],"restricts":[67],"on":[71,124],"samples":[73],"generated":[74],"by":[75],"exponential":[77],"moving":[78],"average":[79],"previously":[81],"policies.":[83],"By":[84],"integrating":[85],"self-constraint":[87],"mechanism":[88],"into":[89],"off-policy":[90],"methods,":[91],"our":[92,112,131],"method":[93,133],"facilitates":[94],"non-conservative":[98],"while":[100],"avoiding":[101],"collapse":[103],"setting.":[107],"Theoretical":[108],"results":[109,114],"show":[110],"approach":[113],"nearly":[117],"monotonically":[118],"improved":[119],"reference":[120],"policy.":[121],"Extensive":[122],"experiments":[123],"D4RL":[126],"MuJoCo":[127],"domain":[128],"demonstrate":[129],"proposed":[132],"achieves":[134],"state-of-the-art":[135],"performance":[136],"among":[137],"methods.":[141]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-10-18T00:00:00"}
