{"id":"https://openalex.org/W4382703339","doi":"https://doi.org/10.1007/978-3-031-36021-3_30","title":"Solving Complex Sequential Decision-Making Problems by\u00a0Deep Reinforcement Learning with\u00a0Heuristic Rules","display_name":"Solving Complex Sequential Decision-Making Problems by\u00a0Deep Reinforcement Learning with\u00a0Heuristic Rules","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4382703339","doi":"https://doi.org/10.1007/978-3-031-36021-3_30"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-36021-3_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-36021-3_30","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":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Solving_Complex_Sequential_Decision-Making_Problems_by_Deep_Reinforcement_Learning_with_Heuristic_Rules/24144627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085593383","display_name":"Thanh Thi Nguyen","orcid":"https://orcid.org/0000-0001-9709-1663"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Thanh Thi Nguyen","raw_affiliation_strings":["Deakin University, Geelong, VIC, Australia"],"affiliations":[{"raw_affiliation_string":"Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838885","display_name":"Cuong Nguyen","orcid":"https://orcid.org/0000-0002-0871-5129"},"institutions":[{"id":"https://openalex.org/I70348806","display_name":"Universit\u00e9 Polytechnique Hauts-de-France","ror":"https://ror.org/02ezch769","country_code":"FR","type":"education","lineage":["https://openalex.org/I70348806"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cuong M. Nguyen","raw_affiliation_strings":["Universit\u00e9 Polytechnique Hauts-de-France, Valenciennes, France"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Polytechnique Hauts-de-France, Valenciennes, France","institution_ids":["https://openalex.org/I70348806"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059877507","display_name":"Thien Huynh\u2010The","orcid":"https://orcid.org/0000-0002-9172-2935"},"institutions":[{"id":"https://openalex.org/I4210148201","display_name":"Ho Chi Minh City University of Technology and Education","ror":"https://ror.org/05hzn5427","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210148201"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Thien Huynh-The","raw_affiliation_strings":["Ho Chi Minh City University of Technology and Education, Ho Chi Minh City, Vietnam"],"affiliations":[{"raw_affiliation_string":"Ho Chi Minh City University of Technology and Education, Ho Chi Minh City, Vietnam","institution_ids":["https://openalex.org/I4210148201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062525719","display_name":"Quoc\u2010Viet Pham","orcid":"https://orcid.org/0000-0002-9485-9216"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Quoc-Viet Pham","raw_affiliation_strings":["Trinity College Dublin (TCD), The University of Dublin, Dublin, Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin (TCD), The University of Dublin, Dublin, Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051219382","display_name":"Quoc Viet Hung Nguyen","orcid":"https://orcid.org/0000-0002-9687-1315"},"institutions":[{"id":"https://openalex.org/I11701301","display_name":"Griffith University","ror":"https://ror.org/02sc3r913","country_code":"AU","type":"education","lineage":["https://openalex.org/I11701301"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quoc Viet Hung Nguyen","raw_affiliation_strings":["Griffith University, Gold Coast, QLD, Australia"],"affiliations":[{"raw_affiliation_string":"Griffith University, Gold Coast, QLD, Australia","institution_ids":["https://openalex.org/I11701301"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033585021","display_name":"Imran Razzak","orcid":"https://orcid.org/0000-0002-3930-6600"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Imran Razzak","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000635267","display_name":"Vijay Janapa Reddi","orcid":"https://orcid.org/0000-0002-5259-7721"},"institutions":[{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay Janapa Reddi","raw_affiliation_strings":["Harvard University, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5085593383"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":2.6293,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.90782029,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"298","last_page":"305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9850000143051147,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8780209422111511},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8354402780532837},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.7660816311836243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7471470832824707},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.604710578918457},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5879819393157959},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5809947848320007},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5095029473304749},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.42369693517684937},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06410491466522217}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8780209422111511},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8354402780532837},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.7660816311836243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7471470832824707},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.604710578918457},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5879819393157959},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5809947848320007},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5095029473304749},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.42369693517684937},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06410491466522217},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-031-36021-3_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-36021-3_30","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:figshare.com:article/24144627","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Solving_Complex_Sequential_Decision-Making_Problems_by_Deep_Reinforcement_Learning_with_Heuristic_Rules/24144627","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:research-repository.griffith.edu.au:10072/425898","is_oa":true,"landing_page_url":"http://hdl.handle.net/10072/425898","pdf_url":null,"source":{"id":"https://openalex.org/S4306402548","display_name":"Griffith Research Online (Griffith University, Queensland, Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I11701301","host_organization_name":"Griffith University","host_organization_lineage":["https://openalex.org/I11701301"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference output"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/24144627","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Solving_Complex_Sequential_Decision-Making_Problems_by_Deep_Reinforcement_Learning_with_Heuristic_Rules/24144627","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2260756217","https://openalex.org/W2795688094","https://openalex.org/W2908261578","https://openalex.org/W2965723696","https://openalex.org/W2994446013","https://openalex.org/W3005355833","https://openalex.org/W3034311880","https://openalex.org/W3095669803","https://openalex.org/W3117423974","https://openalex.org/W3173672478"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2035653613","https://openalex.org/W1583422155","https://openalex.org/W3213252596","https://openalex.org/W1649619740","https://openalex.org/W1534006406"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
