{"id":"https://openalex.org/W4205444807","doi":"https://doi.org/10.1007/s10994-021-06083-7","title":"Improve generated adversarial imitation learning with reward variance regularization","display_name":"Improve generated adversarial imitation learning with reward variance regularization","publication_year":2022,"publication_date":"2022-01-03","ids":{"openalex":"https://openalex.org/W4205444807","doi":"https://doi.org/10.1007/s10994-021-06083-7"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-021-06083-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06083-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06083-7.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06083-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011458940","display_name":"Yi-Feng Zhang","orcid":"https://orcid.org/0000-0001-8834-4921"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi-Feng Zhang","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8834-4921","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024630977","display_name":"Fan-Ming Luo","orcid":"https://orcid.org/0000-0003-1062-8726"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan-Ming Luo","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342263","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1732-9545"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5011458940"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":{"value":3290,"currency":"USD","value_usd":3290},"apc_paid":null,"fwci":7.4806,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.97439857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"111","issue":"3","first_page":"977","last_page":"995"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9957000017166138,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9943000078201294,"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/discriminator","display_name":"Discriminator","score":0.9659655690193176},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7442838549613953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6956062316894531},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6824051141738892},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6787436008453369},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6641455888748169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6471884846687317},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5780885815620422},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5628500580787659},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5351601243019104},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.4769365191459656},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4424595832824707},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4230636656284332},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18562868237495422},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1826859712600708},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08370354771614075}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9659655690193176},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7442838549613953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956062316894531},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6824051141738892},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6787436008453369},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6641455888748169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6471884846687317},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5780885815620422},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5628500580787659},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5351601243019104},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.4769365191459656},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4424595832824707},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4230636656284332},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18562868237495422},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1826859712600708},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08370354771614075},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-021-06083-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06083-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06083-7.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-021-06083-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-06083-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-06083-7.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[{"id":"https://openalex.org/G4366907579","display_name":null,"funder_award_id":"2020AAA0107200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5469316478","display_name":null,"funder_award_id":"61876077","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"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4205444807.pdf","grobid_xml":"https://content.openalex.org/works/W4205444807.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1906772730","https://openalex.org/W1931877416","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2060314721","https://openalex.org/W2260756217","https://openalex.org/W2290104316","https://openalex.org/W2566467060","https://openalex.org/W2740210681","https://openalex.org/W2766610320","https://openalex.org/W2883057932","https://openalex.org/W2890026535","https://openalex.org/W2892806280","https://openalex.org/W2899188163","https://openalex.org/W2963219401","https://openalex.org/W2963654596","https://openalex.org/W2963712524","https://openalex.org/W2995551516","https://openalex.org/W3043572173","https://openalex.org/W4214717370","https://openalex.org/W6638018090","https://openalex.org/W6677916085","https://openalex.org/W6680724558","https://openalex.org/W6718092244","https://openalex.org/W6735913928","https://openalex.org/W6741002519"],"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/W2995777218"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}