{"id":"https://openalex.org/W4388543772","doi":"https://doi.org/10.1109/access.2023.3331728","title":"CARL: A Synergistic Framework for Causal Reinforcement Learning","display_name":"CARL: A Synergistic Framework for Causal Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388543772","doi":"https://doi.org/10.1109/access.2023.3331728"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3331728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3331728","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10314482.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10314482.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087616129","display_name":"Arqu\u00edmides M\u00e9ndez-Molina","orcid":"https://orcid.org/0000-0002-2441-5265"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Arqu\u00edmides M\u00e9ndez-Molina","raw_affiliation_strings":["Instituto Nacional de Astrofísica, Óptica y Electrónica, San Andrés Cholula, Puebla, Mexico"],"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrofísica, Óptica y Electrónica, San Andrés Cholula, Puebla, Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035687300","display_name":"Eduardo F. Morales","orcid":"https://orcid.org/0000-0002-7618-8762"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Eduardo F. Morales","raw_affiliation_strings":["Instituto Nacional de Astrofísica, Óptica y Electrónica, San Andrés Cholula, Puebla, Mexico"],"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrofísica, Óptica y Electrónica, San Andrés Cholula, Puebla, Mexico","institution_ids":["https://openalex.org/I39824353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044189592","display_name":"Luis Enrique Sucar","orcid":"https://orcid.org/0000-0002-3685-5567"},"institutions":[{"id":"https://openalex.org/I39824353","display_name":"National Institute of Astrophysics, Optics and Electronics","ror":"https://ror.org/00bpmmc63","country_code":"MX","type":"facility","lineage":["https://openalex.org/I39824353"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"L. Enrique Sucar","raw_affiliation_strings":["Instituto Nacional de Astrofísica, Óptica y Electrónica, San Andrés Cholula, Puebla, Mexico"],"affiliations":[{"raw_affiliation_string":"Instituto Nacional de Astrofísica, Óptica y Electrónica, San Andrés Cholula, Puebla, Mexico","institution_ids":["https://openalex.org/I39824353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087616129"],"corresponding_institution_ids":["https://openalex.org/I39824353"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.037,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81777307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"11","issue":null,"first_page":"126462","last_page":"126481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9779999852180481,"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/T10260","display_name":"Software Engineering Research","score":0.974399983882904,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8484674692153931},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.729718029499054},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7161707282066345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7073823809623718},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.665519654750824},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.653672456741333},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6308974623680115},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4526391923427582},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3560931980609894},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10893583297729492}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8484674692153931},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.729718029499054},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7161707282066345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7073823809623718},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.665519654750824},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.653672456741333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6308974623680115},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4526391923427582},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3560931980609894},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10893583297729492},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3331728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3331728","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10314482.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:71b20d853e75481fae375b2590808b5a","is_oa":true,"landing_page_url":"https://doaj.org/article/71b20d853e75481fae375b2590808b5a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 126462-126481 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3331728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3331728","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10314482.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1393953593","display_name":null,"funder_award_id":"A1-S-43346","funder_id":"https://openalex.org/F4320321739","funder_display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda"},{"id":"https://openalex.org/G6958583472","display_name":null,"funder_award_id":"A1-S-","funder_id":"https://openalex.org/F4320321739","funder_display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda"}],"funders":[{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388543772.pdf","grobid_xml":"https://content.openalex.org/works/W4388543772.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1491843047","https://openalex.org/W1980035368","https://openalex.org/W2121517924","https://openalex.org/W2128088446","https://openalex.org/W2143891888","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2477696559","https://openalex.org/W2766447205","https://openalex.org/W2806905826","https://openalex.org/W2979225831","https://openalex.org/W2981030070","https://openalex.org/W2982316857","https://openalex.org/W3000239305","https://openalex.org/W3020831056","https://openalex.org/W3096161794","https://openalex.org/W3112027221","https://openalex.org/W3130962444","https://openalex.org/W3182663209","https://openalex.org/W3209710554","https://openalex.org/W3213774989","https://openalex.org/W4214717370","https://openalex.org/W4236605548","https://openalex.org/W4306309788","https://openalex.org/W4309786668","https://openalex.org/W4320559856","https://openalex.org/W4382203289","https://openalex.org/W6636774213","https://openalex.org/W6637967152","https://openalex.org/W6680657880","https://openalex.org/W6686823217","https://openalex.org/W6716227286","https://openalex.org/W6735810065","https://openalex.org/W6739416393","https://openalex.org/W6742245242","https://openalex.org/W6744838376","https://openalex.org/W6751973938","https://openalex.org/W6752252196","https://openalex.org/W6763081524","https://openalex.org/W6769196198","https://openalex.org/W6774121513","https://openalex.org/W6779619272","https://openalex.org/W6781045951","https://openalex.org/W6784188657","https://openalex.org/W6787532554","https://openalex.org/W6790818437","https://openalex.org/W6795769471","https://openalex.org/W6803914020","https://openalex.org/W6838872269","https://openalex.org/W6846209249","https://openalex.org/W6850017302"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W4294738724"],"abstract_inverted_index":{"Causal":[0],"Reinforcement":[1,78],"Learning":[2,79],"(CRL)":[3],"is":[4,141,201],"an":[5,138,235],"emerging":[6],"field":[7],"where":[8,112,137,152,245],"two":[9],"essential":[10],"areas":[11],"for":[12,81,110],"the":[13,23,35,90,115,153,164,167,172,177,206,229,239,246],"development":[14],"of":[15,34,37,45,117,130,166,174,224,231],"artificial":[16],"intelligence":[17],"are":[18,156],"integrated.":[19],"Existing":[20],"works":[21],"in":[22,93,124,133,180,190],"area":[24],"have":[25],"shown":[26],"how":[27,54],"causality":[28],"can":[29,216],"contribute":[30],"to":[31,55,59,88,119,143,158,204,220,233,242,250],"mitigate":[32],"some":[33],"limitations":[36],"reinforcement":[38,57],"learning":[39,49,58,83,92,165,192],"(RL),":[40],"ranging":[41],"from":[42],"data-inefficiency,":[43],"lack":[44],"interpretability,":[46],"and":[47,84,147,196],"long":[48],"times,":[50],"among":[51],"others.":[52],"However,":[53],"use":[56],"support":[60],"causal":[61,86,122,145,208,214],"discovery":[62],"(CD)":[63],"has":[64],"so":[65],"far":[66],"been":[67],"less":[68],"explored.":[69],"In":[70,100],"this":[71],"article,":[72],"we":[73],"introduce":[74],"CARL,":[75],"a":[76,101,221],"Causality-Aware":[77],"framework":[80],"simultaneously":[82],"using":[85,150],"models":[87,123,146,155,215],"speed-up":[89],"police":[91],"online":[94],"Markov":[95],"decision":[96],"process":[97],"(MDP)":[98],"settings.":[99],"synergistic":[102],"way,":[103],"our":[104,185],"method":[105,186],"alternates":[106],"between:":[107],"(i)":[108],"(RL":[109,149],"CD),":[111,151],"it":[113,200],"promotes":[114],"selection":[116],"actions":[118,160],"obtain":[120],"better":[121,188],"fewer":[125],"episodes":[126,232],"than":[127,193],"traditional":[128,194],"methods":[129],"obtaining":[131],"data":[132],"RL,":[134],"(ii)":[135],"(CD),":[136],"score-based":[139],"algorithm":[140],"used":[142,157],"learn":[144,205,234],"(iii)":[148],"learned":[154,213],"select":[159],"that":[161,184],"speed":[162],"up":[163],"optimal":[168,236],"policy":[169,191],"by":[170],"reducing":[171,227],"number":[173,230],"interactions":[175],"with":[176,253],"environment.":[178],"Experiments":[179],"simulated":[181],"environments":[182],"show":[183],"achieves":[187],"results":[189],"model-free":[195],"model-based":[197],"algorithms":[198],"while":[199],"also":[202,211],"able":[203],"underlying":[207],"models.":[209],"We":[210],"showhowthe":[212],"be":[217,251],"directly":[218],"transferred":[219],"similar":[222],"task":[223],"greater":[225],"complexity":[226],"significantly":[228],"policy.":[237],"Finally,":[238],"method\u2019s":[240],"scalability":[241],"high-dimensional":[243],"states,":[244],"action-value":[247],"function":[248],"needs":[249],"represented":[252],"deep":[254],"neural":[255],"networks,":[256],"was":[257],"verified.":[258]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}