{"id":"https://openalex.org/W4363649029","doi":"https://doi.org/10.1109/ciss56502.2023.10089681","title":"Offline Reinforcement Learning for Price-Based Demand Response Program Design","display_name":"Offline Reinforcement Learning for Price-Based Demand Response Program Design","publication_year":2023,"publication_date":"2023-03-22","ids":{"openalex":"https://openalex.org/W4363649029","doi":"https://doi.org/10.1109/ciss56502.2023.10089681"},"language":"en","primary_location":{"id":"doi:10.1109/ciss56502.2023.10089681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss56502.2023.10089681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","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/A5084579868","display_name":"Ce Xu","orcid":"https://orcid.org/0009-0006-4741-9273"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ce Xu","raw_affiliation_strings":["Stony Brook University Stony Brook,Department of Electrical and Computer Engineering,NY,USA,11794"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University Stony Brook,Department of Electrical and Computer Engineering,NY,USA,11794","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036929070","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-8855-5160"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Amazon,Seattle,WA,USA,98109"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon,Seattle,WA,USA,98109","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100919859","display_name":"Yue Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Zhao","raw_affiliation_strings":["Stony Brook University Stony Brook,Department of Electrical and Computer Engineering,NY,USA,11794"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University Stony Brook,Department of Electrical and Computer Engineering,NY,USA,11794","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10603","display_name":"Smart Grid Energy Management","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12546","display_name":"Smart Parking Systems Research","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11954","display_name":"Energy Efficiency and Management","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9149100184440613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8063481450080872},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6429004669189453},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.6172567009925842},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.5584913492202759},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.506388783454895},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49640876054763794},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.45570075511932373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4341510832309723},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4220116436481476},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41660308837890625},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37532204389572144},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.21327590942382812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9149100184440613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063481450080872},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6429004669189453},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.6172567009925842},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.5584913492202759},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.506388783454895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49640876054763794},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.45570075511932373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4341510832309723},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4220116436481476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41660308837890625},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37532204389572144},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.21327590942382812},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss56502.2023.10089681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss56502.2023.10089681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1541754180","https://openalex.org/W2024998154","https://openalex.org/W2343935207","https://openalex.org/W2598902357","https://openalex.org/W2725922920","https://openalex.org/W2736601468","https://openalex.org/W2789695935","https://openalex.org/W2795276745","https://openalex.org/W2876152140","https://openalex.org/W2899328950","https://openalex.org/W2901974325","https://openalex.org/W2963382853","https://openalex.org/W2992494815","https://openalex.org/W3034169784","https://openalex.org/W3036248464","https://openalex.org/W3122528762","https://openalex.org/W3177367445","https://openalex.org/W3212259171","https://openalex.org/W4214717370","https://openalex.org/W4221145154","https://openalex.org/W4298857966","https://openalex.org/W6685444567","https://openalex.org/W6732060498","https://openalex.org/W6760822370","https://openalex.org/W6789492919"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2937181779","https://openalex.org/W3096874164","https://openalex.org/W3167472281","https://openalex.org/W2146763310","https://openalex.org/W2182304831","https://openalex.org/W1556532828","https://openalex.org/W1511927616","https://openalex.org/W4312002974","https://openalex.org/W4284974072"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"price-based":[3],"demand":[4],"response":[5],"(DR)":[6],"program":[7],"design":[8,82],"by":[9,128],"offline":[10,26,73,89,112],"Reinforcement":[11],"Learning":[12],"(RL)":[13],"with":[14,33,51],"data":[15,62,98],"collected":[16],"from":[17],"smart":[18],"meters":[19],"is":[20,58,68,104,119],"studied.":[21],"Unlike":[22],"online":[23,131],"RL":[24,27,74,113,132],"approaches,":[25],"does":[28],"not":[29],"need":[30],"to":[31,81,122],"interact":[32],"consumers":[34],"in":[35],"the":[36,107,110,123,129],"real":[37],"world":[38],"and":[39,44,75,100],"thus":[40],"has":[41],"great":[42],"cost-effectiveness":[43],"safety":[45],"advantages.":[46],"A":[47,60],"sequential":[48],"decision-making":[49],"process":[50],"a":[52,96],"Markov":[53],"Decision":[54],"Process":[55],"(MDP)":[56],"framework":[57],"formulated.":[59],"novel":[61],"augmentation":[63],"method":[64],"based":[65],"on":[66,94],"bootstrapping":[67],"developed.":[69],"Deep":[70],"Q-network":[71],"(DQN)-based":[72],"policy":[76],"evaluation":[77],"algorithms":[78],"are":[79,92],"developed":[80,88,111],"high-performance":[83],"DR":[84],"pricing":[85],"policies.":[86],"The":[87],"learning":[90],"methods":[91,114],"evaluated":[93],"both":[95],"real-world":[97],"set":[99],"simulation":[101],"environments.":[102],"It":[103],"demonstrated":[105],"that":[106,118],"performance":[108,117,125],"of":[109],"achieve":[115],"excellent":[116],"very":[120],"close":[121],"ideal":[124],"bound":[126],"provided":[127],"state-of-the-art":[130],"algorithms.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}