{"id":"https://openalex.org/W4294967798","doi":"https://doi.org/10.1007/978-3-031-15934-3_32","title":"Bi-level Optimization Method for Automatic Reward Shaping of Reinforcement Learning","display_name":"Bi-level Optimization Method for Automatic Reward Shaping of Reinforcement Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4294967798","doi":"https://doi.org/10.1007/978-3-031-15934-3_32"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-15934-3_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-15934-3_32","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":"conference-paper","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/A5038868705","display_name":"Ludi Wang","orcid":"https://orcid.org/0000-0001-6962-766X"},"institutions":[{"id":"https://openalex.org/I4210166468","display_name":"Beijing Aerospace Flight Control Center","ror":"https://ror.org/007a14354","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210166468"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ludi Wang","raw_affiliation_strings":["Beijing Aerospace Automatic Control Institute, Beijing, 100854, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Aerospace Automatic Control Institute, Beijing, 100854, China","institution_ids":["https://openalex.org/I4210166468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061131295","display_name":"Zhaolei Wang","orcid":"https://orcid.org/0000-0001-7121-6237"},"institutions":[{"id":"https://openalex.org/I4210166468","display_name":"Beijing Aerospace Flight Control Center","ror":"https://ror.org/007a14354","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210166468"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaolei Wang","raw_affiliation_strings":["Beijing Aerospace Automatic Control Institute, Beijing, 100854, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Aerospace Automatic Control Institute, Beijing, 100854, China","institution_ids":["https://openalex.org/I4210166468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112862487","display_name":"Qinghai Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210166468","display_name":"Beijing Aerospace Flight Control Center","ror":"https://ror.org/007a14354","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210166468"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghai Gong","raw_affiliation_strings":["Beijing Aerospace Automatic Control Institute, Beijing, 100854, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Aerospace Automatic Control Institute, Beijing, 100854, China","institution_ids":["https://openalex.org/I4210166468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210166468"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"382","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973000288009644,"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":0.9973000288009644,"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/T14011","display_name":"Elevator Systems and Control","score":0.920799970626831,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9179999828338623,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8601970672607422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7814273834228516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5834017992019653},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5047096014022827},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49636679887771606},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48740914463996887},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4863065183162689},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.4547693729400635},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4214229881763458},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.41919374465942383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3814222812652588},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3474813401699066},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13670459389686584}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8601970672607422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7814273834228516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5834017992019653},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5047096014022827},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49636679887771606},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48740914463996887},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4863065183162689},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.4547693729400635},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4214229881763458},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.41919374465942383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3814222812652588},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3474813401699066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13670459389686584},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-15934-3_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-15934-3_32","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1453801241","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2963523627","https://openalex.org/W3174282399","https://openalex.org/W3206540493"],"related_works":["https://openalex.org/W2055541046","https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4361026739","https://openalex.org/W3024399153","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2276682880","https://openalex.org/W2128492082"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
