{"id":"https://openalex.org/W4283273407","doi":"https://doi.org/10.1145/3538637.3538752","title":"Offline training of multi-agent reinforcement agents for grid-interactive buildings control","display_name":"Offline training of multi-agent reinforcement agents for grid-interactive buildings control","publication_year":2022,"publication_date":"2022-06-22","ids":{"openalex":"https://openalex.org/W4283273407","doi":"https://doi.org/10.1145/3538637.3538752"},"language":"en","primary_location":{"id":"doi:10.1145/3538637.3538752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3538637.3538752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth ACM International Conference on Future Energy Systems","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/A5000554005","display_name":"Kingsley Nweye","orcid":"https://orcid.org/0000-0003-1239-5540"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kingsley Nweye","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zoltan Nagy","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoltan Nagy","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461675","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-6615-6601"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041257347","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0003-1546-752X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9598000049591064,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9598000049591064,"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"}},{"id":"https://openalex.org/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.9580000042915344,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T14011","display_name":"Elevator Systems and Control","score":0.9480999708175659,"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/computer-science","display_name":"Computer science","score":0.7157021164894104},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7096709609031677},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.6350250840187073},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5079155564308167},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4587955176830292},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.41189032793045044},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37392157316207886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36464831233024597},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1145378053188324}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7157021164894104},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7096709609031677},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.6350250840187073},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5079155564308167},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4587955176830292},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.41189032793045044},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37392157316207886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36464831233024597},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1145378053188324},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3538637.3538752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3538637.3538752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirteenth ACM International Conference on Future Energy Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2883362962","https://openalex.org/W2901645090","https://openalex.org/W2982984621","https://openalex.org/W3024350433","https://openalex.org/W3090789943","https://openalex.org/W3106664044","https://openalex.org/W3121342653"],"related_works":["https://openalex.org/W8539471","https://openalex.org/W3471107","https://openalex.org/W929682","https://openalex.org/W5435649","https://openalex.org/W2683128","https://openalex.org/W5081013","https://openalex.org/W4651166","https://openalex.org/W5779190","https://openalex.org/W14769209","https://openalex.org/W4955089"],"abstract_inverted_index":{"Advanced":[0],"controllers":[1],"such":[2],"as":[3,132],"model":[4],"predictive":[5],"control":[6,11,40],"and":[7,15,42,101],"reinforcement":[8,51],"learning":[9,52,135],"(RL)":[10],"have":[12],"both":[13],"advantages":[14],"disadvantages":[16],"that":[17,31,74,123],"prevent":[18],"them":[19],"from":[20,63,109,125],"being":[21],"implemented":[22],"in":[23,56,117],"real":[24,49],"world":[25],"problems.":[26],"Building":[27],"upon":[28],"prior":[29],"research":[30],"highlighted":[32],"the":[33,58,64,75,78,88,91,97,118,133],"need":[34],"for":[35,38,48,84],"standardizing":[36],"environments":[37],"building":[39],"research,":[41],"inspired":[43],"by":[44],"recently":[45],"introduced":[46],"challenges":[47],"life":[50],"control,":[53],"we":[54],"demonstrate":[55],"CityLearn,":[57],"effect":[59],"of":[60,67,77,90],"training":[61,86,108],"off-line":[62],"fixed":[65],"logs":[66],"an":[68,110],"external":[69],"behavior":[70],"policy.":[71],"We":[72],"show":[73],"design":[76],"rule":[79],"based":[80],"controller":[81],"(RBC)":[82],"used":[83],"offline":[85,107,134],"affects":[87],"performance":[89,116,131],"RL":[92,121],"agents":[93,122],"when":[94],"evaluated":[95],"on":[96],"average":[98],"daily":[99],"peak":[100],"net":[102],"electric":[103],"consumption.":[104],"While":[105],"longer":[106],"optimized":[111],"RBC":[112,128],"leads":[113],"to":[114],"improved":[115],"long":[119],"run,":[120],"learn":[124],"a":[126],"simplified":[127],"risk":[129],"poorer":[130],"period":[136],"increases.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}