{"id":"https://openalex.org/W4411346089","doi":"https://doi.org/10.1145/3679240.3734670","title":"Reinforcement Learning for Building Control: Direct Actuator or PI-Mediated Control?","display_name":"Reinforcement Learning for Building Control: Direct Actuator or PI-Mediated Control?","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411346089","doi":"https://doi.org/10.1145/3679240.3734670"},"language":"en","primary_location":{"id":"doi:10.1145/3679240.3734670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3679240.3734670","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734670","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734670","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aniket Dixit","orcid":"https://orcid.org/0009-0002-5172-5776"},"institutions":[{"id":"https://openalex.org/I73417466","display_name":"Coventry University","ror":"https://ror.org/01tgmhj36","country_code":"GB","type":"education","lineage":["https://openalex.org/I73417466"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Aniket Dixit","raw_affiliation_strings":["Coventry University, Coventry, Coventry, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0002-5172-5776","affiliations":[{"raw_affiliation_string":"Coventry University, Coventry, Coventry, United Kingdom","institution_ids":["https://openalex.org/I73417466"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Faizan Ahmed","orcid":"https://orcid.org/0009-0008-2466-9207"},"institutions":[{"id":"https://openalex.org/I73417466","display_name":"Coventry University","ror":"https://ror.org/01tgmhj36","country_code":"GB","type":"education","lineage":["https://openalex.org/I73417466"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Faizan Ahmed","raw_affiliation_strings":["Coventry University, Coventry, Coventry, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0008-2466-9207","affiliations":[{"raw_affiliation_string":"Coventry University, Coventry, Coventry, United Kingdom","institution_ids":["https://openalex.org/I73417466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066204863","display_name":"James Brusey","orcid":"https://orcid.org/0000-0002-2710-6927"},"institutions":[{"id":"https://openalex.org/I73417466","display_name":"Coventry University","ror":"https://ror.org/01tgmhj36","country_code":"GB","type":"education","lineage":["https://openalex.org/I73417466"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Brusey","raw_affiliation_strings":["Coventry University, Coventry, Coventry, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-2710-6927","affiliations":[{"raw_affiliation_string":"Coventry University, Coventry, Coventry, United Kingdom","institution_ids":["https://openalex.org/I73417466"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73417466"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16764147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"962","last_page":"967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9871000051498413,"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"}},"topics":[{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9871000051498413,"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/T12093","display_name":"Greenhouse Technology and Climate Control","score":0.9409000277519226,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9021999835968018,"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":0.757209300994873},{"id":"https://openalex.org/keywords/actuator","display_name":"Actuator","score":0.7256968021392822},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.6516644954681396},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6404573321342468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.512717604637146},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4569466710090637},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.44798827171325684},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.43921664357185364},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2731885313987732},{"id":"https://openalex.org/keywords/temperature-control","display_name":"Temperature control","score":0.2076328694820404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20306921005249023},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.10085827112197876}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.757209300994873},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.7256968021392822},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.6516644954681396},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6404573321342468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.512717604637146},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4569466710090637},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.44798827171325684},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.43921664357185364},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2731885313987732},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.2076328694820404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20306921005249023},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.10085827112197876}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3679240.3734670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3679240.3734670","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734670","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3679240.3734670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3679240.3734670","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3679240.3734670","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411346089.pdf","grobid_xml":"https://content.openalex.org/works/W4411346089.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2957897705","https://openalex.org/W3020978263","https://openalex.org/W3090789943","https://openalex.org/W3209188603"],"related_works":["https://openalex.org/W2002388147","https://openalex.org/W3098928304","https://openalex.org/W2394883510","https://openalex.org/W4310083477","https://openalex.org/W4320922540","https://openalex.org/W82747921","https://openalex.org/W1989195983","https://openalex.org/W4234906596","https://openalex.org/W4229591372","https://openalex.org/W2071544734"],"abstract_inverted_index":{"Building":[0,49],"control":[1,123,158,181,200,217,232],"systems":[2],"typically":[3],"use":[4],"either":[5],"setpoint":[6,23,105,137,223],"regulation,":[7],"where":[8,183,197],"controllers":[9],"determine":[10],"optimal":[11],"setpoints":[12,188],"for":[13,189,213],"low-level":[14,191],"systems,":[15],"or":[16],"direct":[17,73,121,198],"actuator":[18,122,167,199],"control,":[19],"which":[20],"bypasses":[21],"the":[22,48,163,170],"layer.Despite":[24],"widespread":[25],"hierarchical":[26],"approaches,":[27],"empirical":[28,211],"evidence":[29,177],"comparing":[30],"these":[31],"strategies":[32,218],"remains":[33],"limited.This":[34],"paper":[35],"presents":[36],"a":[37,82,179],"systematic":[38],"evaluation":[39],"of":[40,166],"both":[41],"paradigms":[42],"using":[43,63,219],"reinforcement":[44,220],"learning":[45],"(RL)":[46],"with":[47,77,99,114,129,222],"Optimization":[50],"Performance":[51],"Test":[52],"(BOPTEST)":[53],"framework":[54],"[1].We":[55],"implement":[56],"and":[57,68,80,95,150,231],"compare:":[58],"(1)":[59],"setpoint-trained":[60],"RL":[61,75,185,203],"agents":[62,76],"PPO":[64],"[8],":[65],"DQN":[66],"[6],":[67],"A2C":[69],"[5]":[70],"algorithms,":[71,79],"(2)":[72],"actuation-controlled":[74],"identical":[78],"(3)":[81],"conventional":[83],"PI":[84],"controller":[85],"baseline.Experiments":[86],"span":[87],"two":[88],"simulation":[89],"environments":[90],"(BESTEST":[91],"Hydronic":[92],"Heat":[93],"Pump":[94],"BESTEST":[96],"Air":[97],"systems)":[98],"constant":[100],"electricity":[101],"pricing.Results":[102],"demonstrate":[103],"that":[104],"regulation":[106,138,224],"achieves":[107],"near-perfect":[108],"thermal":[109],"comfort":[110,131],"(>99%":[111],"discomfort":[112,134],"reduction)":[113],"modest":[115],"energy":[116,126],"cost":[117],"increases":[118],"(4.8-5.0%),":[119],"while":[120,193],"offers":[124],"smaller":[125],"penalties":[127],"(1.8-3.2%)":[128],"substantial":[130],"improvements":[132],"(>80%":[133],"reduction).Most":[135],"significantly,":[136],"consistently":[139],"demonstrated":[140],"faster":[141],"learning,":[142,221],"requiring":[143],"48-79%":[144],"fewer":[145],"training":[146,229],"steps":[147],"across":[148],"algorithms":[149],"environments.The":[151],"setpointtrained":[152],"approach":[153],"also":[154,194],"exhibited":[155],"38%":[156],"lower":[157],"signal":[159],"variance":[160],"(measured":[161],"as":[162],"standard":[164],"deviation":[165],"commands)":[168],"over":[169],"14-day":[171],"testing":[172],"period.These":[173],"findings":[174],"provide":[175],"quantitative":[176],"supporting":[178],"two-level":[180],"architecture,":[182],"an":[184,202],"agent":[186,204],"optimizes":[187],"existing":[190],"controllers,":[192],"identifying":[195],"conditions":[196],"by":[201],"may":[205],"be":[206],"advantageous.Our":[207],"research":[208],"contributes":[209],"valuable":[210],"insights":[212],"designing":[214],"energy-efficient":[215],"building":[216],"offering":[225],"significant":[226],"advantages":[227],"in":[228],"efficiency":[230],"stability.":[233]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}