{"id":"https://openalex.org/W2216374114","doi":"https://doi.org/10.1007/978-3-642-40705-5_2","title":"Self-Practice Imitation Learning from Weak Policy","display_name":"Self-Practice Imitation Learning from Weak Policy","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2216374114","doi":"https://doi.org/10.1007/978-3-642-40705-5_2","mag":"2216374114"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-40705-5_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-40705-5_2","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","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/A5070849903","display_name":"Qing Da","orcid":"https://orcid.org/0000-0003-2200-0098"},"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":"Qing Da","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210046, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210046, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","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":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210046, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210046, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100621138","display_name":"Zhi\u2010Hua Zhou","orcid":"https://orcid.org/0000-0003-0746-1494"},"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":"Zhi-Hua Zhou","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210046, China","National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, 210046, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, People's Republic of China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070849903"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25726141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9706000089645386,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9706000089645386,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9422000050544739,"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/computer-science","display_name":"Computer science","score":0.8351724147796631},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7912955284118652},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.7664279937744141},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6102538704872131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5377744436264038},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5210292339324951},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5012702941894531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4444091320037842},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4240495264530182},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41062843799591064},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11092808842658997},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.09941956400871277},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06450521945953369}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8351724147796631},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7912955284118652},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7664279937744141},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6102538704872131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5377744436264038},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5210292339324951},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5012702941894531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4444091320037842},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4240495264530182},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41062843799591064},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11092808842658997},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.09941956400871277},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06450521945953369},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-642-40705-5_2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-40705-5_2","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.6545","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.6545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cs.nju.edu.cn/zhouzh/zhouzh.files/publication/psl13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1490760466","https://openalex.org/W1504694836","https://openalex.org/W1523792757","https://openalex.org/W1540685400","https://openalex.org/W1566073559","https://openalex.org/W1570448133","https://openalex.org/W1576660662","https://openalex.org/W1986014385","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2121863487","https://openalex.org/W2125055259","https://openalex.org/W2129018774","https://openalex.org/W2150818585","https://openalex.org/W2153635508","https://openalex.org/W2156909104","https://openalex.org/W2163387410","https://openalex.org/W2165484066","https://openalex.org/W2166302491","https://openalex.org/W2184441712","https://openalex.org/W2799061466","https://openalex.org/W2903158431","https://openalex.org/W2911283634","https://openalex.org/W2911964244","https://openalex.org/W4205687621","https://openalex.org/W4214717370","https://openalex.org/W4230674625","https://openalex.org/W6814762204"],"related_works":["https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2795910581","https://openalex.org/W3131296902","https://openalex.org/W2605292759","https://openalex.org/W2783543950","https://openalex.org/W3044461295","https://openalex.org/W3038067716","https://openalex.org/W3106528330","https://openalex.org/W1744884320"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
