{"id":"https://openalex.org/W4309801643","doi":"https://doi.org/10.1145/3563357.3566165","title":"Behavioural cloning based RL agents for district energy management","display_name":"Behavioural cloning based RL agents for district energy management","publication_year":2022,"publication_date":"2022-11-09","ids":{"openalex":"https://openalex.org/W4309801643","doi":"https://doi.org/10.1145/3563357.3566165"},"language":"en","primary_location":{"id":"doi:10.1145/3563357.3566165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563357.3566165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03851408","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080822016","display_name":"Sharath Ram Kumar","orcid":"https://orcid.org/0000-0001-6778-4485"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR","SG"],"is_corresponding":false,"raw_author_name":"Sharath Ram Kumar","raw_affiliation_strings":["Univ. Grenoble Alpes, Grenoble, France and Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, Grenoble, France and Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054946593","display_name":"Arvind Easwaran","orcid":"https://orcid.org/0000-0002-9628-3847"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Arvind Easwaran","raw_affiliation_strings":["Nanyang Technological University, Singapore","Nanyang Technological University [Singapour] (50 Nanyang Ave, Singapour 639798 - Singapore)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Nanyang Technological University [Singapour] (50 Nanyang Ave, Singapour 639798 - Singapore)","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004639668","display_name":"Beno\u00eet Delinchant","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Delinchant","raw_affiliation_strings":["Univ. Grenoble Alpes, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046814285","display_name":"R\u00e9my Rigo\u2010Mariani","orcid":"https://orcid.org/0000-0002-3098-9572"},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Remy Rigo-Mariani","raw_affiliation_strings":["Univ. Grenoble Alpes, Grenoble, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, Grenoble, France","institution_ids":["https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.652,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82655814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"466","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10603","display_name":"Smart Grid Energy Management","score":0.9983999729156494,"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":0.9983999729156494,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9825000166893005,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8811979293823242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628142833709717},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6848933100700378},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6498540639877319},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6277979016304016},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.5616661310195923},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5523008704185486},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5208159685134888},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5043717622756958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44454240798950195},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42990005016326904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3451285660266876},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12089064717292786}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8811979293823242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628142833709717},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6848933100700378},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6498540639877319},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6277979016304016},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.5616661310195923},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5523008704185486},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5208159685134888},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5043717622756958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44454240798950195},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42990005016326904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3451285660266876},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12089064717292786},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3563357.3566165","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3563357.3566165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03851408v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03851408","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM SIGEnergy Workshop on Reinforcement Learning for Energy Management in Buildings & Cities (RLEM), Nov 2022, Boston, United States. ⟨10.1145/3563357.3566165⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03851408v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03851408","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM SIGEnergy Workshop on Reinforcement Learning for Energy Management in Buildings & Cities (RLEM), Nov 2022, Boston, United States. ⟨10.1145/3563357.3566165⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2062912550","https://openalex.org/W2582843567","https://openalex.org/W2901645090","https://openalex.org/W3101780148","https://openalex.org/W3106664044","https://openalex.org/W3128707967","https://openalex.org/W3164631379","https://openalex.org/W3194662390","https://openalex.org/W3209275630","https://openalex.org/W4291923700","https://openalex.org/W6891925286"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2665305151"],"abstract_inverted_index":{"In":[0],"this":[1,60],"work,":[2],"we":[3],"discuss":[4],"a":[5,12,27,43,64,92,109,118,122],"method":[6],"to":[7,41,57,82,105,136],"incorporate":[8],"domain":[9],"knowledge":[10],"into":[11,35],"Reinforcement":[13],"Learning":[14],"(RL)":[15],"environment":[16],"through":[17],"the":[18,24,73,77,84,97,113,130],"process":[19],"of":[20,26,132],"behavioral":[21],"cloning,":[22],"in":[23,72,91],"context":[25],"district":[28],"energy":[29,86],"management":[30],"system.":[31],"Prior":[32],"knowledge,":[33],"encoded":[34],"heuristic":[36],"rule-based":[37,115],"programs,":[38],"is":[39,55,80],"used":[40,56,81],"initialize":[42],"policy":[44],"network":[45],"for":[46,88],"an":[47,52],"RL":[48,53,124],"agent,":[49],"after":[50],"which":[51],"algorithm":[54],"improve":[58],"on":[59],"by":[61],"optimizing":[62],"against":[63],"reward":[65,144],"function.":[66],"The":[67],"key":[68],"ideas":[69],"are":[70],"implemented":[71],"CityLearn":[74],"framework,":[75],"where":[76],"resulting":[78,98],"controller":[79],"manage":[83],"electrical":[85],"storage":[87],"5":[89],"buildings":[90],"district.":[93],"We":[94,127],"demonstrate":[95],"that":[96],"agents":[99,138],"offer":[100],"measurable":[101],"performance":[102],"gains":[103],"compared":[104],"existing":[106],"baselines,":[107],"offering":[108],"3.8%":[110],"improvement":[111,120],"over":[112,121],"underlying":[114],"controller,":[116],"and":[117],"20%":[119],"pure":[123],"based":[125],"controller.":[126],"also":[128],"illustrate":[129],"possibility":[131],"using":[133],"imitation":[134],"learning":[135],"develop":[137],"with":[139],"desirable":[140],"characteristics":[141],"without":[142],"explicit":[143],"shaping.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}