{"id":"https://openalex.org/W4300980650","doi":"https://doi.org/10.48550/arxiv.2209.15626","title":"B2RL: An open-source Dataset for Building Batch Reinforcement Learning","display_name":"B2RL: An open-source Dataset for Building Batch Reinforcement Learning","publication_year":2022,"publication_date":"2022-09-30","ids":{"openalex":"https://openalex.org/W4300980650","doi":"https://doi.org/10.48550/arxiv.2209.15626"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2209.15626","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15626","pdf_url":"https://arxiv.org/pdf/2209.15626","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.15626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101600786","display_name":"Hsin\u2010Yu Liu","orcid":"https://orcid.org/0000-0002-9316-2150"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liu, Hsin-Yu","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002036322","display_name":"Xiaohan Fu","orcid":"https://orcid.org/0009-0002-5614-5922"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fu, Xiaohan","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101689740","display_name":"Bharathan Balaji","orcid":"https://orcid.org/0000-0002-9490-2018"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Balaji, Bharathan","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749692","display_name":"Rajesh Gupta","orcid":"https://orcid.org/0000-0001-7833-0235"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gupta, Rajesh","raw_affiliation_strings":["University of California, San Diego"],"affiliations":[{"raw_affiliation_string":"University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088730125","display_name":"Dezhi Hong","orcid":"https://orcid.org/0000-0001-5224-6043"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hong, Dezhi","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101600786"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.9886999726295471,"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/T12546","display_name":"Smart Parking Systems Research","score":0.9886999726295471,"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/T10121","display_name":"Building Energy and Comfort Optimization","score":0.9531999826431274,"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":0.9021000266075134,"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":0.8313236236572266},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8212450742721558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.791537344455719},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.6732896566390991},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.43585485219955444},{"id":"https://openalex.org/keywords/model-building","display_name":"Model building","score":0.4277648329734802},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4217669665813446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3658822774887085},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.0820959210395813},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06603792309761047}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8313236236572266},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8212450742721558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791537344455719},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.6732896566390991},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.43585485219955444},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.4277648329734802},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4217669665813446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3658822774887085},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0820959210395813},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06603792309761047},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2209.15626","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15626","pdf_url":"https://arxiv.org/pdf/2209.15626","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2209.15626","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2209.15626","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.15626","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15626","pdf_url":"https://arxiv.org/pdf/2209.15626","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Batch":[0,61],"reinforcement":[1],"learning":[2],"(BRL)":[3],"is":[4,51],"an":[5],"emerging":[6],"research":[7],"area":[8],"in":[9,82],"the":[10,25,28,44,96,103,110],"RL":[11],"community.":[12],"It":[13],"learns":[14],"exclusively":[15],"from":[16,68],"static":[17],"datasets":[18,108],"(i.e.":[19],"replay":[20,32,49],"buffers)":[21],"without":[22],"interaction":[23],"with":[24],"environment.":[26],"In":[27,57],"offline":[29],"settings,":[30],"existing":[31],"experiences":[33],"are":[34,102],"used":[35],"as":[36,73,75],"prior":[37],"knowledge":[38],"for":[39,53,109],"BRL":[40,54,93,113],"models":[41],"to":[42,105],"find":[43],"optimal":[45],"policy.":[46],"Thus,":[47],"generating":[48],"buffers":[50,76],"crucial":[52],"model":[55],"benchmark.":[56],"our":[58,69,99],"B2RL":[59],"(Building":[60],"RL)":[62],"dataset,":[63],"we":[64,101],"collected":[65],"real-world":[66],"data":[67],"building":[70,90,107],"management":[71],"systems,":[72],"well":[74],"generated":[77],"by":[78],"several":[79],"behavioral":[80],"policies":[81],"simulation":[83],"environments.":[84],"We":[85],"believe":[86],"it":[87],"could":[88],"help":[89],"experts":[91],"on":[92],"research.":[94],"To":[95],"best":[97],"of":[98,112],"knowledge,":[100],"first":[104],"open-source":[106],"purpose":[111],"learning.":[114]},"counts_by_year":[],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}