{"id":"https://openalex.org/W4403676946","doi":"https://doi.org/10.1109/case59546.2024.10711482","title":"On Efficient Sampling for Reinforcement Learning with Multiple Constraints*","display_name":"On Efficient Sampling for Reinforcement Learning with Multiple Constraints*","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4403676946","doi":"https://doi.org/10.1109/case59546.2024.10711482"},"language":"en","primary_location":{"id":"doi:10.1109/case59546.2024.10711482","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/case59546.2024.10711482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"article","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/A5044965133","display_name":"Qing\u2010Shan Jia","orcid":"https://orcid.org/0000-0002-4683-7215"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qing-Shan Jia","raw_affiliation_strings":["Tsinghua University,CFINS,Department of Automation,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,CFINS,Department of Automation,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032152448","display_name":"Qi Guo","orcid":"https://orcid.org/0000-0001-9198-2270"},"institutions":[{"id":"https://openalex.org/I74872605","display_name":"China Southern Power Grid (China)","ror":"https://ror.org/03hkh9419","country_code":"CN","type":"company","lineage":["https://openalex.org/I74872605"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Guo","raw_affiliation_strings":["China Southern Power Grid Electric Power Research Institute,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"China Southern Power Grid Electric Power Research Institute,Guangzhou,China","institution_ids":["https://openalex.org/I74872605"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044965133"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16511593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2768","last_page":"2773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9682999849319458,"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":0.9682999849319458,"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":0.9508000016212463,"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/T12879","display_name":"Distributed Sensor Networks and Detection Algorithms","score":0.9372000098228455,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8262503147125244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6999053955078125},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4824950695037842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45006290078163147},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3784463107585907},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3644481301307678},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18511700630187988},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10187098383903503}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8262503147125244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6999053955078125},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4824950695037842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45006290078163147},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3784463107585907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3644481301307678},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18511700630187988},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10187098383903503},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case59546.2024.10711482","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/case59546.2024.10711482","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2484571116","https://openalex.org/W2560504659","https://openalex.org/W2964263252","https://openalex.org/W3047623911","https://openalex.org/W3161194236","https://openalex.org/W3203511922","https://openalex.org/W4206497039","https://openalex.org/W4237029372","https://openalex.org/W4254845134","https://openalex.org/W4312542679","https://openalex.org/W4353056919","https://openalex.org/W4380371586","https://openalex.org/W4380873470","https://openalex.org/W4385490607","https://openalex.org/W4391995188","https://openalex.org/W4392944875","https://openalex.org/W4402570199","https://openalex.org/W6632064144","https://openalex.org/W6849235091"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,99],"has":[2],"attracted":[3],"growing":[4],"interest":[5],"in":[6,14,35,43],"many":[7],"decision":[8],"making":[9],"problems.":[10],"A":[11],"special":[12],"feature":[13],"automation":[15],"is":[16,86],"the":[17,31,48,54,59,62,95],"pervasive":[18],"existence":[19],"of":[20,33,61,64],"multiple":[21],"simulation-based":[22,101],"constraints.":[23],"Existing":[24],"algorithms":[25],"may":[26],"behave":[27],"inefficient":[28],"when":[29],"evaluating":[30],"feasibility":[32],"policies":[34],"this":[36,40,44,78,84,91],"case.":[37],"We":[38,89],"consider":[39],"important":[41],"problem":[42,57],"work,":[45],"and":[46,100],"make":[47],"following":[49],"contributions.":[50],"First,":[51],"we":[52,72,81],"convert":[53],"constrained":[55],"Q-learning":[56],"to":[58,76],"maximization":[60],"probability":[63],"correct":[65],"selection":[66],"with":[67],"simulation":[68],"budget":[69],"constraint.":[70],"Second,":[71],"provide":[73],"an":[74],"algorithm":[75,85],"solve":[77],"problem.":[79],"Third,":[80],"show":[82],"that":[83],"asymptotically":[87],"optimal.":[88],"hope":[90],"work":[92],"might":[93],"strengthen":[94],"connection":[96],"between":[97],"reinforcement":[98],"optimization.":[102]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}