{"id":"https://openalex.org/W4383604734","doi":"https://doi.org/10.48550/arxiv.2307.02752","title":"Offline Reinforcement Learning with Imbalanced Datasets","display_name":"Offline Reinforcement Learning with Imbalanced Datasets","publication_year":2023,"publication_date":"2023-07-06","ids":{"openalex":"https://openalex.org/W4383604734","doi":"https://doi.org/10.48550/arxiv.2307.02752"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.02752","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02752","pdf_url":"https://arxiv.org/pdf/2307.02752","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2307.02752","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105423384","display_name":"L\u00ec Ji\u0101ng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiang, Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738031","display_name":"Sijie Chen","orcid":"https://orcid.org/0000-0001-5263-9189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Sijie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058194829","display_name":"Jielin Qiu","orcid":"https://orcid.org/0000-0002-7384-1324"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Jielin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101855228","display_name":"Haoran Xu","orcid":"https://orcid.org/0009-0005-2477-5737"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Haoran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108743840","display_name":"Wai Kin Victor Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chan, Wai Kin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112906233","display_name":"Zhao Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Zhao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5105423384"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9854000210762024,"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"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9854000210762024,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8028817176818848},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7685366272926331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6760722994804382},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5905587673187256},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5600212216377258},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0656958818435669}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8028817176818848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7685366272926331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6760722994804382},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5905587673187256},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5600212216377258},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0656958818435669},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.02752","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02752","pdf_url":"https://arxiv.org/pdf/2307.02752","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2307.02752","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.02752","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.02752","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02752","pdf_url":"https://arxiv.org/pdf/2307.02752","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383604734.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"The":[0,29],"prevalent":[1],"use":[2],"of":[3,17,20,27,45,56,118,147,153,158,165],"benchmarks":[4],"in":[5,24,59,96,144],"current":[6],"offline":[7,31,60,82,111],"reinforcement":[8],"learning":[9],"(RL)":[10],"research":[11],"has":[12],"led":[13],"to":[14,42,124],"a":[15,67,109,121],"neglect":[16],"the":[18,25,38,43,63,100,116,131,145,156,163],"imbalance":[19],"real-world":[21,30],"dataset":[22,33],"distributions":[23],"development":[26],"models.":[28],"RL":[32,83,112],"is":[34],"often":[35],"imbalanced":[36,57,101,135,148],"over":[37,168],"state":[39,64],"space":[40],"due":[41],"challenge":[44],"exploration":[46],"or":[47],"safety":[48],"considerations.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,78,107],"specify":[54],"properties":[55],"datasets":[58,149],"RL,":[61],"where":[62],"coverage":[65],"follows":[66],"power":[68],"law":[69],"distribution":[70],"characterized":[71],"by":[72,104,134],"skewed":[73],"policies.":[74],"Theoretically":[75],"and":[76],"empirically,":[77],"show":[79],"that":[80,114],"typically":[81],"methods":[84],"based":[85],"on":[86,141],"distributional":[87],"constraints,":[88],"such":[89],"as":[90],"conservative":[91],"Q-learning":[92],"(CQL),":[93],"are":[94],"ineffective":[95],"extracting":[97],"policies":[98],"under":[99],"dataset.":[102],"Inspired":[103],"natural":[105],"intelligence,":[106],"propose":[108],"novel":[110],"method":[113,140,167],"utilizes":[115],"augmentation":[117],"CQL":[119],"with":[120,150],"retrieval":[122],"process":[123],"recall":[125],"past":[126],"related":[127],"experiences,":[128],"effectively":[129],"alleviating":[130],"challenges":[132],"posed":[133],"datasets.":[136],"We":[137],"evaluate":[138],"our":[139,166],"several":[142],"tasks":[143],"context":[146],"varying":[151],"levels":[152],"imbalance,":[154],"utilizing":[155],"variant":[157],"D4RL.":[159],"Empirical":[160],"results":[161],"demonstrate":[162],"superiority":[164],"other":[169],"baselines.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}