{"id":"https://openalex.org/W7164905011","doi":"https://doi.org/10.1145/3744255.3811723","title":"Trans-SAC: Robust and Transferable Maximum Entropy Reinforcement Learning for Heat Pump Control","display_name":"Trans-SAC: Robust and Transferable Maximum Entropy Reinforcement Learning for Heat Pump Control","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7164905011","doi":"https://doi.org/10.1145/3744255.3811723"},"language":null,"primary_location":{"id":"doi:10.1145/3744255.3811723","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744255.3811723","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th 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://doi.org/10.1145/3744255.3811723","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013879483","display_name":"Qiong Huang","orcid":"https://orcid.org/0000-0002-1958-6094"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Qiong Huang","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0002-1958-6094","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133843639","display_name":"Adrian Till Assmuth","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adrian Till Assmuth","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0009-0005-7402-0770","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004584210","display_name":"Felix Langner","orcid":"https://orcid.org/0000-0002-3473-5545"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Langner","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3473-5545","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014228448","display_name":"Veit Hagenmeyer","orcid":"https://orcid.org/0000-0002-3572-9083"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Veit Hagenmeyer","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3572-9083","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040295886","display_name":"Benjamin Sch\u00e4fer","orcid":"https://orcid.org/0000-0003-1607-9748"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Sch\u00e4fer","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1607-9748","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"54"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10121","display_name":"Building Energy and Comfort Optimization","score":0.8323000073432922,"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":0.8323000073432922,"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/T10603","display_name":"Smart Grid Energy Management","score":0.09780000150203705,"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/T11185","display_name":"Integrated Energy Systems Optimization","score":0.02070000022649765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6254000067710876},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.43650001287460327},{"id":"https://openalex.org/keywords/thermal-comfort","display_name":"Thermal comfort","score":0.42179998755455017},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.396699994802475},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.36809998750686646},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.36800000071525574},{"id":"https://openalex.org/keywords/smart-grid","display_name":"Smart grid","score":0.36160001158714294},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3515999913215637},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6292999982833862},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6254000067710876},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.43650001287460327},{"id":"https://openalex.org/C133913538","wikidata":"https://www.wikidata.org/wiki/Q774514","display_name":"Thermal comfort","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.382099986076355},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.36800000071525574},{"id":"https://openalex.org/C10558101","wikidata":"https://www.wikidata.org/wiki/Q689855","display_name":"Smart grid","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2776461528","wikidata":"https://www.wikidata.org/wiki/Q131313","display_name":"Heat pump","level":3,"score":0.3285999894142151},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2779438525","wikidata":"https://www.wikidata.org/wiki/Q5255048","display_name":"Demand response","level":3,"score":0.2955999970436096},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C67212190","wikidata":"https://www.wikidata.org/wiki/Q104851","display_name":"Firmware","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2533999979496002},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3744255.3811723","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744255.3811723","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3744255.3811723","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744255.3811723","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM International Conference on Future and Sustainable Energy Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7371082305908203,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[{"id":"https://openalex.org/G2044937970","display_name":null,"funder_award_id":"VH-NG-1727","funder_id":"https://openalex.org/F4320325698","funder_display_name":"Helmholtz Association"},{"id":"https://openalex.org/G8528268260","display_name":null,"funder_award_id":"bwHPC (bwUniCluster 3.0)","funder_id":"https://openalex.org/F4320325698","funder_display_name":"Helmholtz Association"},{"id":"https://openalex.org/G863695574","display_name":null,"funder_award_id":"Project number 37.12.01","funder_id":"https://openalex.org/F4320325698","funder_display_name":"Helmholtz Association"}],"funders":[{"id":"https://openalex.org/F4320325698","display_name":"Helmholtz Association","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2166313543","https://openalex.org/W2436872002","https://openalex.org/W2553501321","https://openalex.org/W2811440831","https://openalex.org/W2898962279","https://openalex.org/W2901645090","https://openalex.org/W3024350433","https://openalex.org/W3048265338","https://openalex.org/W3083020785","https://openalex.org/W3162079807","https://openalex.org/W3193645253","https://openalex.org/W4206696802","https://openalex.org/W4315480006","https://openalex.org/W4378571872","https://openalex.org/W4386337718","https://openalex.org/W4389265746","https://openalex.org/W4391265349","https://openalex.org/W4406793412","https://openalex.org/W7117541269","https://openalex.org/W7154692704"],"related_works":[],"abstract_inverted_index":{"Residential":[0],"heating":[1],"electrification":[2],"through":[3],"heat":[4,219],"pumps":[5],"is":[6],"a":[7,73,94,115,142,211],"cornerstone":[8],"of":[9,24,144],"building":[10,30,175],"decarbonization,":[11],"yet":[12],"their":[13],"potential":[14],"for":[15,216],"grid":[16],"flexibility":[17],"remains":[18,180],"underutilized":[19],"due":[20,170],"to":[21,43,78,109,171],"the":[22,80,161,198],"difficulty":[23],"scaling":[25],"control":[26,59,75,130],"strategies":[27],"across":[28,53,141],"heterogeneous":[29,146],"stocks.":[31],"Although":[32],"reinforcement":[33],"learning":[34,179],"(RL)":[35],"offers":[36],"model-free":[37],"adaptability,":[38],"standard":[39,162],"approaches":[40],"often":[41],"fail":[42],"scale,":[44],"suffering":[45],"from":[46],"brittle":[47],"policies":[48],"that":[49,61,159],"do":[50],"not":[51],"generalize":[52],"diverse":[54],"thermal":[55],"dynamics":[56],"or":[57],"discrete":[58],"actions":[60],"damage":[62],"hardware.":[63],"To":[64],"address":[65],"this,":[66],"we":[67,113],"introduce":[68],"Trans-SAC":[69,92,209],"(Transferable":[70],"Soft":[71],"Actor-Critic),":[72],"robust":[74,194],"framework":[76],"designed":[77],"solve":[79],"\u201ccold":[81],"start\u201d":[82],"problem":[83],"in":[84,174],"city-scale":[85],"deployments.":[86],"By":[87],"leveraging":[88],"maximum":[89],"entropy":[90],"RL,":[91],"optimizes":[93],"dynamic":[95,121],"trade-off":[96],"between":[97],"reward":[98],"and":[99,123,136,153,177,196,201,213],"entropy,":[100],"ensuring":[101],"continuous,":[102],"hardware-safe":[103],"actuation.":[104],"Unlike":[105],"prior":[106],"work":[107],"limited":[108],"fixed":[110],"temperature":[111],"bands,":[112],"target":[114],"challenging":[116],"time-varying":[117],"comfort":[118],"objective":[119],"under":[120],"pricing":[122],"rigorously":[124],"evaluate":[125],"SAC":[126],"against":[127],"model":[128],"predictive":[129],"(MPC)":[131],"baselines,":[132],"deep":[133],"Q-networks":[134],"(DQN)":[135],"proximal":[137],"policy":[138],"optimization":[139],"(PPO),":[140],"dataset":[143],"ten":[145],"residential":[147],"buildings":[148],"calibrated":[149],"with":[150],"real-world":[151],"weather":[152],"price":[154],"data.":[155],"Our":[156],"experiments":[157],"reveal":[158],"while":[160],"feature-freezing":[163],"technique":[164],"accelerates":[165],"training,":[166],"they":[167],"remain":[168],"suboptimal":[169],"physical":[172],"mismatches":[173],"envelopes,":[176],"independent":[178],"prohibitively":[181],"sample-inefficient.":[182],"In":[183],"contrast,":[184],"Trans-SAC\u2019s":[185],"full-network":[186],"adaptation":[187],"strategy":[188],"successfully":[189],"bridges":[190],"this":[191],"gap,":[192],"enabling":[193],"generalization":[195],"reducing":[197],"training":[199],"time":[200],"significantly":[202],"outperforming":[203],"other":[204],"transfer":[205],"baselines.":[206],"This":[207],"establishes":[208],"as":[210],"viable":[212],"data-efficient":[214],"blueprint":[215],"aggregating":[217],"large-scale":[218],"pump":[220],"fleets":[221],"into":[222],"smart":[223],"buildings.":[224]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-17T00:00:00"}