{"id":"https://openalex.org/W4401752175","doi":"https://doi.org/10.1109/aim55361.2024.10636978","title":"On Sampling Efficiency Optimization in Constrained Reinforcement Learning<sup>*</sup>","display_name":"On Sampling Efficiency Optimization in Constrained Reinforcement Learning<sup>*</sup>","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4401752175","doi":"https://doi.org/10.1109/aim55361.2024.10636978"},"language":"en","primary_location":{"id":"doi:10.1109/aim55361.2024.10636978","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aim55361.2024.10636978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","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"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,CFINS,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.11419293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"966","last_page":"971"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9437999725341797,"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":0.9437999725341797,"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":0.9068999886512756,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6670777797698975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5862938761711121},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5108168125152588},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41692623496055603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3843879997730255},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19972547888755798},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07828488945960999}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6670777797698975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5862938761711121},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5108168125152588},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41692623496055603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3843879997730255},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19972547888755798},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07828488945960999},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aim55361.2024.10636978","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/aim55361.2024.10636978","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1498432697","https://openalex.org/W1995713768","https://openalex.org/W2484957131","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/W4213251304","https://openalex.org/W4237029372","https://openalex.org/W4312542679","https://openalex.org/W4313597256","https://openalex.org/W4353056919","https://openalex.org/W4380371586","https://openalex.org/W4380873470","https://openalex.org/W4391995188","https://openalex.org/W4392944875","https://openalex.org/W6632064144","https://openalex.org/W6849235091"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Constrained":[0],"reinforcement":[1],"learning":[2,88],"is":[3,102],"of":[4,13,46,77,109],"great":[5],"practical":[6],"interest":[7],"due":[8,32],"to":[9,30,33,93,104],"the":[10,18,23,41,44,72,75,95,98,107,112],"pervasive":[11],"existence":[12],"constraints":[14,20,27],"in":[15,54],"applications.":[16],"Beyond":[17],"typical":[19],"directly":[21],"on":[22,39,67],"state":[24],"space,":[25,100],"simulation-based":[26],"are":[28],"harder":[29],"address,":[31],"noisy":[34],"and":[35,43,57,74,80],"time":[36],"consuming":[37],"evaluation":[38],"both":[40],"performance":[42,73],"feasibility":[45,76],"a":[47,78],"policy.":[48],"We":[49],"consider":[50],"this":[51,55],"important":[52],"problem":[53],"work":[56],"make":[58],"two":[59],"contributions.":[60],"First,":[61],"we":[62,89],"develop":[63,90],"an":[64,91],"algorithm":[65,92],"based":[66],"Q-learning":[68],"that":[69],"iteratively":[70],"improves":[71],"policy":[79],"show":[81],"its":[82],"global":[83],"convergence.":[84],"Second,":[85],"for":[86],"online":[87],"control":[94],"sampling":[96],"among":[97],"action":[99],"which":[101],"shown":[103],"asymptotically":[105],"maximize":[106],"probability":[108],"correctly":[110],"selecting":[111],"best":[113],"feasible":[114],"action.":[115]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}