{"id":"https://openalex.org/W4416428811","doi":"https://doi.org/10.1016/j.cpes.2025.07.003","title":"Historical optimization decision-assisted adversarial inverse reinforcement learning for smart home energy management","display_name":"Historical optimization decision-assisted adversarial inverse reinforcement learning for smart home energy management","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4416428811","doi":"https://doi.org/10.1016/j.cpes.2025.07.003"},"language":"en","primary_location":{"id":"doi:10.1016/j.cpes.2025.07.003","doi":"https://doi.org/10.1016/j.cpes.2025.07.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cpes.2025.07.003","pdf_url":null,"source":{"id":"https://openalex.org/S5407051299","display_name":"Cyber-Physical Energy Systems","issn_l":"3050-7448","issn":["3050-7448"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cyber-Physical Energy Systems","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.cpes.2025.07.003","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026971814","display_name":"Liang Yu","orcid":"https://orcid.org/0000-0001-5015-0320","observed_orcids":["https://orcid.org/0000-0001-5015-0320"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liang Yu","raw_affiliation_strings":["College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":"https://orcid.org/0000-0001-5015-0320","affiliations":[{"raw_affiliation_string":"College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006768032","display_name":"Jinrong He","orcid":"https://orcid.org/0000-0001-5272-7218","observed_orcids":["https://orcid.org/0000-0001-5272-7218"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiadong He","raw_affiliation_strings":["College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434661","display_name":"Zhiqiang Chen","orcid":"https://orcid.org/0000-0002-2109-7767","observed_orcids":["https://orcid.org/0000-0002-2109-7767"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Chen","raw_affiliation_strings":["College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025367353","display_name":"Dingfan Zhang","orcid":"https://orcid.org/0009-0008-0469-1263","observed_orcids":["https://orcid.org/0009-0008-0469-1263"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingfan Zhang","raw_affiliation_strings":["College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Automation, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033274994","display_name":"Dong Peng Yue","orcid":"https://orcid.org/0000-0001-7810-9338","observed_orcids":["https://orcid.org/0000-0001-7810-9338"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yue","raw_affiliation_strings":["The Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5026971814"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":{"value":0,"currency":"USD","value_usd":0},"apc_paid":{"value":0,"currency":"USD","value_usd":0},"fwci":0.2299,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48831193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"2","issue":"1","first_page":"73","last_page":"80"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9970999956130981,"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":0.9970999956130981,"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/T12222","display_name":"IoT-based Smart Home Systems","score":0.0010999999940395355,"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/T10121","display_name":"Building Energy and Comfort Optimization","score":0.000699999975040555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/smart-home-energy-management","display_name":"smart home energy management","score":0.9879999756813049},{"id":"https://openalex.org/keywords/adversarial-inverse-reinforcement-learning","display_name":"adversarial inverse reinforcement learning","score":0.9860000014305115},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8370000123977661},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.7689999938011169},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.6690000295639038},{"id":"https://openalex.org/keywords/deterministic-optimization","display_name":"deterministic optimization","score":0.7429999709129333},{"id":"https://openalex.org/keywords/renewable-energy-utilization","display_name":"renewable energy utilization","score":0.5929999947547913},{"id":"https://openalex.org/keywords/electricity-price-uncertainty","display_name":"electricity price uncertainty","score":0.6520000100135803},{"id":"https://openalex.org/keywords/data-efficiency","display_name":"data efficiency","score":0.48100000619888306},{"id":"https://openalex.org/keywords/online-energy-management","display_name":"online energy management","score":0.4490000009536743}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7361000180244446},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6470000147819519},{"id":"https://openalex.org/C7817414","wikidata":"https://www.wikidata.org/wiki/Q1779504","display_name":"Energy management","level":3,"score":0.5763999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5685999989509583},{"id":"https://openalex.org/C10558101","wikidata":"https://www.wikidata.org/wiki/Q689855","display_name":"Smart grid","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5202000141143799},{"id":"https://openalex.org/C507571656","wikidata":"https://www.wikidata.org/wiki/Q848436","display_name":"Home automation","level":2,"score":0.4918999969959259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4819999933242798},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.46309998631477356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.36899998784065247},{"id":"https://openalex.org/C206658404","wikidata":"https://www.wikidata.org/wiki/Q12725","display_name":"Electricity","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C188573790","wikidata":"https://www.wikidata.org/wiki/Q12705","display_name":"Renewable energy","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32190001010894775},{"id":"https://openalex.org/C2781260460","wikidata":"https://www.wikidata.org/wiki/Q6139999","display_name":"Energy management system","level":4,"score":0.3203999996185303},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.30300000309944153},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.cpes.2025.07.003","doi":"https://doi.org/10.1016/j.cpes.2025.07.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cpes.2025.07.003","pdf_url":null,"source":{"id":"https://openalex.org/S5407051299","display_name":"Cyber-Physical Energy Systems","issn_l":"3050-7448","issn":["3050-7448"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cyber-Physical Energy Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.cpes.2025.07.003","doi":"https://doi.org/10.1016/j.cpes.2025.07.003","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.cpes.2025.07.003","pdf_url":null,"source":{"id":"https://openalex.org/S5407051299","display_name":"Cyber-Physical Energy Systems","issn_l":"3050-7448","issn":["3050-7448"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Cyber-Physical Energy Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.9853000044822693}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G184828240","display_name":null,"funder_award_id":"62192751","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2663811732","display_name":null,"funder_award_id":"62233010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2309225173","https://openalex.org/W2625632007","https://openalex.org/W2974232099","https://openalex.org/W4223973792","https://openalex.org/W4281567217","https://openalex.org/W4285106921","https://openalex.org/W4292551110","https://openalex.org/W4297095234","https://openalex.org/W4323275929","https://openalex.org/W4389383601","https://openalex.org/W4399697107","https://openalex.org/W4404212169","https://openalex.org/W4406019916","https://openalex.org/W4406070916","https://openalex.org/W4408423437","https://openalex.org/W4409560673"],"related_works":[],"abstract_inverted_index":{"Smart":[0],"home":[1],"energy":[2,11,42,100],"management":[3,43,101],"(SHEM)":[4],"plays":[5],"a":[6,63,125,152,164],"vital":[7],"role":[8],"in":[9,82,143],"reducing":[10],"costs":[12],"and":[13,59,89,132,206,222],"enhancing":[14],"the":[15,21,114,144,159,169,179,188,198,218,225],"utilization":[16],"of":[17,47,66,84,203,224],"renewable":[18,57],"energy.":[19],"Among":[20],"various":[22],"SHEM":[23,69],"approaches,":[24],"deep":[25],"reinforcement":[26,110],"learning":[27,111,182],"(DRL)-based":[28],"methods":[29,70],"have":[30],"attracted":[31],"significant":[32],"attention":[33],"due":[34],"to":[35,38,150,174],"their":[36,72],"ability":[37],"support":[39],"real-time,":[40],"online":[41],"without":[44,187],"requiring":[45],"forecasts":[46],"uncertain":[48,204],"parameters":[49,205],"such":[50],"as":[51,140],"dynamic":[52],"electricity":[53],"prices,":[54],"outdoor":[55],"temperature,":[56],"generation,":[58],"load":[60],"demand.":[61],"However,":[62],"major":[64],"limitation":[65],"existing":[67],"DRL-based":[68],"is":[71,148,172],"reliance":[73],"on":[74,107],"manually":[75,207],"designed":[76,149],"reward":[77,87,192,209],"functions,":[78],"which":[79,147],"adds":[80],"complexity":[81],"terms":[83],"selecting":[85],"appropriate":[86],"structures":[88],"tuning":[90],"parameters.":[91],"To":[92],"address":[93],"this":[94,96],"challenge,":[95],"paper":[97],"proposes":[98],"an":[99,133,183],"method":[102,196],"for":[103,190,200],"smart":[104],"homes":[105],"based":[106],"adversarial":[108],"inverse":[109],"(AIRL).":[112],"In":[113],"proposed":[115,195,226],"method,":[116],"historical":[117,130],"optimal":[118,137],"decisions":[119,138],"are":[120],"first":[121],"obtained":[122],"by":[123,163],"solving":[124],"deterministic":[126],"optimization":[127,134],"problem":[128],"using":[129,213],"data":[131,215,220],"solver.":[135],"These":[136],"serve":[139],"expert":[141,156],"demonstrations":[142,157],"AIRL":[145],"module,":[146],"train":[151],"discriminator":[153],"that":[154,177],"distinguishes":[155],"from":[158],"state-action":[160],"transitions":[161,176],"generated":[162],"DRL":[165],"agent":[166,170],"policy.":[167],"Simultaneously,":[168],"policy":[171,186],"updated":[173],"generate":[175],"confuse":[178],"discriminator,":[180],"thereby":[181],"effective":[184],"control":[185],"need":[189,199],"explicit":[191],"engineering.":[193],"The":[194],"eliminates":[197],"predictive":[201],"models":[202],"crafted":[208],"functions.":[210],"Simulation":[211],"results":[212],"real-world":[214],"traces":[216],"validate":[217],"effectiveness,":[219],"efficiency,":[221],"robustness":[223],"method.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-09T09:14:12.587421","created_date":"2025-11-20T00:00:00"}