{"id":"https://openalex.org/W4403678485","doi":"https://doi.org/10.1109/case59546.2024.10711588","title":"Enhancing Predictability in Deep Reinforcement Learning for Building Temperature Control","display_name":"Enhancing Predictability in Deep Reinforcement Learning for Building Temperature Control","publication_year":2024,"publication_date":"2024-08-28","ids":{"openalex":"https://openalex.org/W4403678485","doi":"https://doi.org/10.1109/case59546.2024.10711588"},"language":"en","primary_location":{"id":"doi:10.1109/case59546.2024.10711588","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/case59546.2024.10711588","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/A5073281532","display_name":"Luca Ferrarini","orcid":"https://orcid.org/0000-0001-7598-8971"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luca Ferrarini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053688399","display_name":"A. Valentini","orcid":"https://orcid.org/0000-0002-6129-1230"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alberto Valentini","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5073281532"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19995059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1228","last_page":"1233"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.5651999711990356,"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":0.5651999711990356,"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/predictability","display_name":"Predictability","score":0.9192650318145752},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8495344519615173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6506805419921875},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5916407704353333},{"id":"https://openalex.org/keywords/temperature-control","display_name":"Temperature control","score":0.5424233078956604},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4869752824306488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41814643144607544},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.18102243542671204},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14521118998527527},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07747271656990051},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.07191365957260132}],"concepts":[{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.9192650318145752},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8495344519615173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506805419921875},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5916407704353333},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.5424233078956604},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4869752824306488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41814643144607544},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.18102243542671204},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14521118998527527},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07747271656990051},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.07191365957260132},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/case59546.2024.10711588","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/case59546.2024.10711588","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"},{"id":"pmh:oai:re.public.polimi.it:11311/1287448","is_oa":false,"landing_page_url":"https://hdl.handle.net/11311/1287448","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2278079993","https://openalex.org/W2612281180","https://openalex.org/W2736601468","https://openalex.org/W3023586494","https://openalex.org/W3090789943","https://openalex.org/W3163621993","https://openalex.org/W3201919935","https://openalex.org/W3205868665","https://openalex.org/W4214717370","https://openalex.org/W4388918432","https://openalex.org/W6704571135","https://openalex.org/W6788186211"],"related_works":["https://openalex.org/W2726467123","https://openalex.org/W2064726690","https://openalex.org/W4252678288","https://openalex.org/W4254065731","https://openalex.org/W1607297154","https://openalex.org/W4210820789","https://openalex.org/W4237782192","https://openalex.org/W2913177154","https://openalex.org/W4235131201","https://openalex.org/W4232793539"],"abstract_inverted_index":{"In":[0,53],"recent":[1],"years,":[2],"machine":[3],"learning-based":[4],"methods":[5],"have":[6],"become":[7],"increasingly":[8],"popular":[9],"for":[10,66,147],"addressing":[11],"control":[12,19,39,69],"problems.":[13],"Within":[14],"the":[15,58,67,82,88,116,145],"context":[16],"of":[17,51,60,70,91,154],"temperature":[18,68],"in":[20],"buildings,":[21],"reinforcement":[22,63,133],"learning":[23,64,134],"algorithms":[24],"stand":[25],"out":[26],"as":[27,105],"an":[28,61],"appealing":[29],"model-free":[30],"and":[31,46,109,123],"fast":[32],"real-time":[33,148],"execution":[34],"alternative":[35],"to":[36,86,97,115,140],"classical":[37],"model-based":[38,77],"methods.":[40],"However,":[41],"these":[42],"techniques":[43],"lack":[44],"interpretability":[45],"require":[47],"a":[48,71,75,102,106,151],"significant":[49],"amount":[50,153],"data.":[52,155],"this":[54],"paper,":[55],"we":[56],"investigate":[57],"application":[59],"actor-critic":[62,92],"algorithm":[65],"medium-size":[72],"building":[73],"through":[74],"specific":[76],"training":[78],"approach.":[79],"More":[80],"specifically,":[81],"goal":[83],"is":[84],"here":[85],"enhance":[87],"predictive":[89,142],"capabilities":[90],"schemes":[93],"by":[94],"proposing":[95],"extensions":[96],"state-of-the-art":[98],"algorithms,":[99],"which":[100],"integrate":[101],"simplified":[103],"model":[104,141],"state":[107],"predictor":[108],"incorporate":[110],"future":[111],"disturbances.":[112],"This":[113],"leads":[114],"so-called":[117],"Recursive":[118],"Actor-Critic,":[119,122],"Look-Ahead":[120],"Trajectory":[121],"Augmented":[124],"Actor-Critic":[125],"schemes.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"such":[131],"improved":[132],"approaches":[135],"can":[136],"achieve":[137],"performance":[138],"comparable":[139],"control,":[143],"without":[144],"need":[146],"optimization":[149],"nor":[150],"huge":[152]},"counts_by_year":[],"updated_date":"2026-03-04T07:04:00.330322","created_date":"2025-10-10T00:00:00"}