{"id":"https://openalex.org/W4391673314","doi":"https://doi.org/10.48550/arxiv.2402.04869","title":"Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy","display_name":"Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy","publication_year":2024,"publication_date":"2024-02-07","ids":{"openalex":"https://openalex.org/W4391673314","doi":"https://doi.org/10.48550/arxiv.2402.04869"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2402.04869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.04869","pdf_url":"https://arxiv.org/pdf/2402.04869","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":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2402.04869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076948208","display_name":"Ruichu Cai","orcid":"https://orcid.org/0000-0001-8972-167X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Cai, Ruichu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595405","display_name":"Siyang Huang","orcid":"https://orcid.org/0009-0002-3828-040X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Siyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100574061","display_name":"Jie Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100344522","display_name":"Wei Chen","orcid":"https://orcid.org/0000-0003-0065-3610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101642516","display_name":"Yan Zeng","orcid":"https://orcid.org/0000-0003-2275-6354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113115892","display_name":"Keli Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Keli","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Fuchun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411381","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-5204-2929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5092002405","display_name":"Zhifeng Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Zhifeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5076948208"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11182","display_name":"Auction Theory and Applications","score":0.8974999785423279,"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"}},"topics":[{"id":"https://openalex.org/T11182","display_name":"Auction Theory and Applications","score":0.8974999785423279,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8769999742507935,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.8309000134468079,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6026707887649536},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4930574595928192},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4706909954547882},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.43884342908859253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43847334384918213},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.42012906074523926},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.42006099224090576},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4032996892929077},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3568061888217926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2838054299354553},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.24063900113105774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17761120200157166},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11921373009681702}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6026707887649536},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4930574595928192},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4706909954547882},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.43884342908859253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43847334384918213},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.42012906074523926},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.42006099224090576},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4032996892929077},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3568061888217926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2838054299354553},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.24063900113105774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17761120200157166},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11921373009681702}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2402.04869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.04869","pdf_url":"https://arxiv.org/pdf/2402.04869","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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2402.04869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2402.04869","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2402.04869","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.04869","pdf_url":"https://arxiv.org/pdf/2402.04869","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1334762759","display_name":null,"funder_award_id":"6212202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1540529280","display_name":null,"funder_award_id":"62206061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G167464954","display_name":null,"funder_award_id":"U24A20233","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2236945492","display_name":null,"funder_award_id":"2021ZD0111501","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G3271603901","display_name":null,"funder_award_id":"62122022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4662166426","display_name":null,"funder_award_id":"62406078","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5691792714","display_name":null,"funder_award_id":"62476163","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5957623925","display_name":null,"funder_award_id":"2023B151","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6464829129","display_name":null,"funder_award_id":"2023B1515120020","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8007181506","display_name":null,"funder_award_id":"62122022","funder_id":"https://openalex.org/F4320333688","funder_display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China"},{"id":"https://openalex.org/G8341450228","display_name":null,"funder_award_id":"62206064","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8369339599","display_name":null,"funder_award_id":"122022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8513333314","display_name":null,"funder_award_id":"2021ZD01","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8819344089","display_name":null,"funder_award_id":"U24A2023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320333688","display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391673314.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912","https://openalex.org/W2145821588"],"abstract_inverted_index":{"As":[0],"a":[1,36,103],"key":[2],"component":[3],"to":[4,134,184],"intuitive":[5],"cognition":[6],"and":[7,41,122,161,167,192],"reasoning":[8],"solutions":[9],"in":[10,39,144,155],"human":[11],"intelligence,":[12],"causal":[13,52,68,81,117,126,193],"knowledge":[14],"provides":[15],"great":[16],"potential":[17],"for":[18,116,128],"reinforcement":[19],"learning":[20,92,119,191],"(RL)":[21],"agents'":[22],"interpretability":[23],"towards":[24],"decision-making":[25],"by":[26],"helping":[27],"reduce":[28],"the":[29,48,61,67,76,80,85,94,98,124,135,145,150,165,170,185],"searching":[30],"space.":[31],"However,":[32],"there":[33],"is":[34],"still":[35],"considerable":[37],"gap":[38],"discovering":[40],"incorporating":[42],"causality":[43],"into":[44,84],"RL,":[45],"which":[46,73,196],"hinders":[47],"rapid":[49],"development":[50],"of":[51,64,93,137,169,188],"RL.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57,74,101,148],"consider":[58],"explicitly":[59],"modeling":[60],"generation":[62],"process":[63,88],"states":[65],"with":[66,89,105,198],"graphical":[69],"model,":[70],"based":[71],"on":[72],"augment":[75],"policy.":[77],"We":[78],"formulate":[79],"structure":[82,118,127,194],"updating":[83],"RL":[86],"interaction":[87],"active":[90],"intervention":[91,143],"environment.":[95],"To":[96],"optimize":[97],"derived":[99],"objective,":[100],"propose":[102],"framework":[104],"theoretical":[106],"performance":[107,181],"guarantees":[108],"that":[109,140,179],"alternates":[110],"between":[111],"two":[112],"steps:":[113],"using":[114,123],"interventions":[115],"during":[120,131],"exploration":[121],"learned":[125],"policy":[129,190],"guidance":[130],"exploitation.":[132],"Due":[133],"lack":[136],"public":[138],"benchmarks":[139],"allow":[141],"direct":[142],"state":[146],"space,":[147],"design":[149],"root":[151],"cause":[152],"localization":[153],"task":[154],"our":[156,180,199],"simulated":[157],"fault":[158],"alarm":[159],"environment":[160],"then":[162],"empirically":[163],"show":[164],"effectiveness":[166],"robustness":[168],"proposed":[171],"method":[172],"against":[173],"state-of-the-art":[174],"baselines.":[175],"Theoretical":[176],"analysis":[177],"shows":[178],"improvement":[182],"attributes":[183],"virtuous":[186],"cycle":[187],"causal-guided":[189],"learning,":[195],"aligns":[197],"experimental":[200],"results.":[201],"Codes":[202],"are":[203],"available":[204],"at":[205],"https://github.com/DMIRLAB-Group/FaultAlarm_RL.":[206]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}