{"id":"https://openalex.org/W2109690886","doi":"https://doi.org/10.1109/coase.2009.5234189","title":"Customized learning algorithms for episodic tasks with acyclic state spaces","display_name":"Customized learning algorithms for episodic tasks with acyclic state spaces","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2109690886","doi":"https://doi.org/10.1109/coase.2009.5234189","mag":"2109690886"},"language":"en","primary_location":{"id":"doi:10.1109/coase.2009.5234189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2009.5234189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Automation Science and Engineering","raw_type":"proceedings-article"},"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/A5111880744","display_name":"Theologos Bountourelis","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theologos Bountourelis","raw_affiliation_strings":["School of Industrial & Systems Engineering, Georgia Institute of Technology, USA","School of Industrial and Systems Engineering, Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial & Systems Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008675858","display_name":"Spyros Reveliotis","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spyros Reveliotis","raw_affiliation_strings":["School of Industrial & Systems Engineering, Georgia Institute of Technology, USA","School of Industrial and Systems Engineering, Georgia Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial & Systems Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"School of Industrial and Systems Engineering, Georgia Institute of Technology, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"627","last_page":"634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.9751999974250793,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9526000022888184,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/computer-science","display_name":"Computer science","score":0.7651557922363281},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7411920428276062},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6396591067314148},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6029018759727478},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6016312837600708},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5368222594261169},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5097753405570984},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4848690927028656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41740575432777405},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0847320556640625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651557922363281},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7411920428276062},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6396591067314148},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6029018759727478},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6016312837600708},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5368222594261169},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5097753405570984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848690927028656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41740575432777405},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0847320556640625},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coase.2009.5234189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2009.5234189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Automation Science and Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.46000000834465027}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1508634047","https://openalex.org/W1515851193","https://openalex.org/W1520252399","https://openalex.org/W1576452626","https://openalex.org/W1943309769","https://openalex.org/W1964005797","https://openalex.org/W1987876419","https://openalex.org/W2009533501","https://openalex.org/W2025486342","https://openalex.org/W2083143894","https://openalex.org/W2099105702","https://openalex.org/W2110235415","https://openalex.org/W2112214730","https://openalex.org/W2122701159","https://openalex.org/W2147967768","https://openalex.org/W2319588593","https://openalex.org/W2334782222","https://openalex.org/W2489939061","https://openalex.org/W2793249117","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W2947302008","https://openalex.org/W3011120880","https://openalex.org/W4307347247","https://openalex.org/W6630247960","https://openalex.org/W6678494045","https://openalex.org/W6703110798"],"related_works":["https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879","https://openalex.org/W797688974","https://openalex.org/W2002978035","https://openalex.org/W2209382646"],"abstract_inverted_index":{"The":[0,23,91],"work":[1],"presented":[2,24,50],"in":[3,70],"this":[4,46],"paper":[5],"provides":[6],"a":[7,61,97],"practical,":[8],"customized":[9],"learning":[10,14],"algorithm":[11,56,67,93],"for":[12,106],"reinforcement":[13],"tasks":[15],"that":[16,48],"evolve":[17],"episodically":[18],"over":[19,101],"acyclic":[20],"state":[21],"spaces.":[22],"results":[25],"are":[26],"motivated":[27],"by":[28,87],"the":[29,54,65,74,79,83,88,102,107],"optimal":[30],"disassembly":[31],"planning":[32],"(ODP)":[33],"problem":[34,47,109],"described":[35],"in,":[36,69],"and":[37,40,78],"they":[38],"complement":[39],"enhance":[41],"some":[42],"earlier":[43],"developments":[44],"on":[45],"were":[49],"in.":[51],"In":[52],"particular,":[53],"proposed":[55],"is":[57,85],"shown":[58],"to":[59,96],"be":[60],"substantial":[62],"improvement":[63],"of":[64],"original":[66],"developed":[68],"terms":[71],"of,":[72],"both,":[73],"involved":[75],"computational":[76],"effort":[77],"attained":[80],"performance,":[81],"where":[82],"latter":[84],"measured":[86],"accumulated":[89],"reward.":[90],"new":[92],"also":[94],"leads":[95],"robust":[98],"performance":[99],"gain":[100],"typical":[103],"Q-learning":[104],"implementations":[105],"considered":[108],"context.":[110]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}