{"id":"https://openalex.org/W3022312285","doi":"https://doi.org/10.1007/978-3-030-47436-2_21","title":"Balancing Exploration and Exploitation in Self-imitation Learning","display_name":"Balancing Exploration and Exploitation in Self-imitation Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3022312285","doi":"https://doi.org/10.1007/978-3-030-47436-2_21","mag":"3022312285"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-47436-2_21","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-47436-2_21","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-47436-2_21.pdf","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":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-47436-2_21.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053436056","display_name":"Chun-Yao Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Yao Kang","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036009069","display_name":"Ming-Syan Chen\u22c6","orcid":"https://orcid.org/0000-0002-0711-8197"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Syan Chen","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053436056"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.275,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52740833,"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":"274","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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":0.989300012588501,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.7948482036590576},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7836848497390747},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.781485378742218},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7355208396911621},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.5986469984054565},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5424448251724243},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5219451785087585},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1380373239517212},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08443009853363037},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06486678123474121},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.059894710779190063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948482036590576},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7836848497390747},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.781485378742218},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7355208396911621},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.5986469984054565},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5424448251724243},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5219451785087585},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1380373239517212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08443009853363037},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06486678123474121},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.059894710779190063},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-47436-2_21","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-47436-2_21","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-47436-2_21.pdf","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:pubmedcentral.nih.gov:7206262","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7206262","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Knowledge Discovery and Data Mining","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-47436-2_21","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-47436-2_21","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-47436-2_21.pdf","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3022312285.pdf","grobid_xml":"https://content.openalex.org/works/W3022312285.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W779494576","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W2158782408","https://openalex.org/W2260756217","https://openalex.org/W2593766708","https://openalex.org/W2614839826","https://openalex.org/W2736601468","https://openalex.org/W2803839069","https://openalex.org/W2885550588","https://openalex.org/W2899205164","https://openalex.org/W2902982219","https://openalex.org/W2909668595","https://openalex.org/W2963160877","https://openalex.org/W2963276097","https://openalex.org/W2963277051","https://openalex.org/W2963523627","https://openalex.org/W2964043796","https://openalex.org/W2964062135","https://openalex.org/W3037207827","https://openalex.org/W6601067093","https://openalex.org/W6603144686","https://openalex.org/W6780559895","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W4310614650"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}