{"id":"https://openalex.org/W7126457891","doi":"https://doi.org/10.5555/3635637.3663027","title":"CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning","display_name":"CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126457891","doi":"https://doi.org/10.5555/3635637.3663027"},"language":"en","primary_location":{"id":"pmh:oai:dare.uva.nl:openaire/1a90265f-c855-4269-a413-d5b66b7b50fa","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/core-towards-scalable-and-efficient-causal-discovery-with-reinforcement-learning(1a90265f-c855-4269-a413-d5b66b7b50fa).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sauter, A, Boteghi, N, Acar, E & Plaat, A 2024, CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning. in AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems : May 6-10, 2024, Auckland, New Zealand. Richland, SC, pp. 1664-1672, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p1664.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dare.uva.nl/personal/pure/en/publications/core-towards-scalable-and-efficient-causal-discovery-with-reinforcement-learning(1a90265f-c855-4269-a413-d5b66b7b50fa).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sauter, A.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sauter, A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Boteghi, Nicol\u00f2","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boteghi, Nicol\u00f2","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Acar, E.; id_orcid 0009-0002-9656-7249","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Acar, E.; id_orcid 0009-0002-9656-7249","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Plaat, Aske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Plaat, Aske","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57313215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9562000036239624,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9562000036239624,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.01119999960064888,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.699400007724762},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5975000262260437},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5059000253677368},{"id":"https://openalex.org/keywords/causal-structure","display_name":"Causal structure","score":0.4848000109195709},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4699999988079071},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.44589999318122864},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4415000081062317}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.699400007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6912999749183655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869000196456909},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6237000226974487},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5059000253677368},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.4848000109195709},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.44589999318122864},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30489999055862427},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:dare.uva.nl:openaire/1a90265f-c855-4269-a413-d5b66b7b50fa","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/core-towards-scalable-and-efficient-causal-discovery-with-reinforcement-learning(1a90265f-c855-4269-a413-d5b66b7b50fa).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sauter, A, Boteghi, N, Acar, E & Plaat, A 2024, CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning. in AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems : May 6-10, 2024, Auckland, New Zealand. Richland, SC, pp. 1664-1672, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p1664.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:dare.uva.nl:openaire/1a90265f-c855-4269-a413-d5b66b7b50fa","is_oa":true,"landing_page_url":"https://dare.uva.nl/personal/pure/en/publications/core-towards-scalable-and-efficient-causal-discovery-with-reinforcement-learning(1a90265f-c855-4269-a413-d5b66b7b50fa).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sauter, A, Boteghi, N, Acar, E & Plaat, A 2024, CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning. in AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems : May 6-10, 2024, Auckland, New Zealand. Richland, SC, pp. 1664-1672, 23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024, Auckland, New Zealand, 6/05/24. < https://www.ifaamas.org/Proceedings/aamas2024/pdfs/p1664.pdf >","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Causal":[0,15],"discovery":[1,70],"is":[2],"the":[3],"challenging":[4],"task":[5],"of":[6],"inferring":[7],"causal":[8,69,79,101],"structure":[9,119],"from":[10,31,81],"data.":[11],"Motivated":[12],"by":[13],"Pearl's":[14],"Hierarchy":[16],"(PCH),":[17],"which":[18],"tells":[19],"us":[20],"that":[21,92],"passive":[22],"observations":[23],"alone":[24],"are":[25],"not":[26],"enough":[27],"to":[28,39,57,76,85,95,106,111],"distinguish":[29],"correlation":[30],"causation,":[32],"there":[33],"has":[34],"been":[35],"a":[36,49,63],"recent":[37],"push":[38],"incorporate":[40],"interventions":[41],"into":[42],"machine":[43],"learning":[44,47,84],"research.":[45],"Reinforcement":[46],"provides":[48],"convenient":[50],"framework":[51],"for":[52,68],"such":[53],"an":[54],"active":[55],"approach":[56,67],"learning.":[58],"This":[59],"paper":[60],"presents":[61],"CORE,":[62],"deep":[64],"reinforcement":[65],"learning-based":[66],"and":[71,98,114,122,128],"intervention":[72],"planning.":[73],"CORE":[74,93,104],"learns":[75],"sequentially":[77],"reconstruct":[78],"graphs":[80,97,108],"data":[82],"while":[83],"perform":[86],"informative":[87],"interventions.":[88],"Our":[89],"results":[90],"demonstrate":[91],"generalizes":[94],"unseen":[96],"efficiently":[99],"uncovers":[100],"structures.":[102],"Furthermore,":[103],"scales":[105],"larger":[107],"with":[109],"up":[110],"10":[112],"variables":[113],"outperforms":[115],"existing":[116],"approaches":[117],"in":[118],"estimation":[120],"accuracy":[121],"sample":[123],"efficiency.":[124],"All":[125],"relevant":[126],"code":[127],"supplementary":[129],"material":[130],"can":[131],"be":[132],"found":[133],"at":[134],"https://github.com/sa-and/CORE.":[135]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}