{"id":"https://openalex.org/W4413392964","doi":"https://doi.org/10.23919/acc63710.2025.11107696","title":"Multi-Agent Causal Dynamics Learning for Temporally Extended Tasks with Reward Machine Inference","display_name":"Multi-Agent Causal Dynamics Learning for Temporally Extended Tasks with Reward Machine Inference","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413392964","doi":"https://doi.org/10.23919/acc63710.2025.11107696"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107696","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118979952","display_name":"Hadi Partovi Aria","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hadi Partovi Aria","raw_affiliation_strings":["Arizona State University,School for Engineering of Matter, Transport and Energy (SEMTE),Tempe,USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School for Engineering of Matter, Transport and Energy (SEMTE),Tempe,USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013789785","display_name":"Zhe Xu","orcid":"https://orcid.org/0000-0002-0440-0912"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Xu","raw_affiliation_strings":["Arizona State University,School for Engineering of Matter, Transport and Energy (SEMTE),Tempe,USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University,School for Engineering of Matter, Transport and Energy (SEMTE),Tempe,USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5118979952"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32233943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3628","last_page":"3633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.963699996471405,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10876","display_name":"Fault Detection and Control Systems","score":0.963699996471405,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9472000002861023,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9355000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7532017230987549},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6864422559738159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.604419469833374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5563485026359558},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5236853361129761},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.5067992806434631},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.16718441247940063},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13550329208374023},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09993681311607361}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7532017230987549},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6864422559738159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.604419469833374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5563485026359558},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5236853361129761},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.5067992806434631},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.16718441247940063},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13550329208374023},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09993681311607361},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107696","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5099999904632568,"display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1497487247","https://openalex.org/W1587663028","https://openalex.org/W2082784990","https://openalex.org/W2972500268","https://openalex.org/W3092156990","https://openalex.org/W4392397303","https://openalex.org/W4393160846","https://openalex.org/W4402264525"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"We":[0,109],"introduce":[1],"an":[2],"approach":[3,78],"called":[4],"Multi-Agent":[5],"State":[6],"Abstraction":[7],"with":[8,127],"Causal":[9],"dynamics":[10],"and":[11,61,73,91],"Reward":[12],"Machine":[13],"Learning":[14],"(Multi-SACReM),":[15],"designed":[16],"to":[17,38,55,68,105],"enhance":[18],"the":[19],"efficiency":[20],"of":[21],"reinforcement":[22],"learning":[23],"(RL)":[24],"in":[25,42,80,135],"multi-agent":[26,136],"environments.":[27,94],"By":[28],"integrating":[29],"causal":[30,64,125],"information":[31,104],"through":[32,112],"state":[33],"abstraction,":[34],"MultiSACReM":[35],"enables":[36],"agents":[37,67,85,101],"learn":[39,86],"more":[40],"effectively":[41,123],"complex,":[43],"dynamic":[44],"settings.":[45,137],"In":[46,95],"our":[47],"framework,":[48],"each":[49],"agent":[50],"employs":[51],"a":[52,98],"reward":[53,128],"machine,":[54],"optimize":[56,74,106],"its":[57],"behavior.":[58,108],"Multi-SACReM":[59,111,122],"identifies":[60],"eliminates":[62],"redundant":[63],"relationships,":[65],"allowing":[66],"focus":[69],"on":[70],"essential":[71],"interactions":[72],"policies":[75],"accordingly.":[76],"Our":[77],"works":[79],"both":[81],"decentralized":[82,116,131],"settings,":[83],"where":[84],"independently":[87],"using":[88,102],"local":[89],"observations,":[90],"centralized":[92,96,118,133],"RL":[93],"RL,":[97],"controller":[99],"coordinates":[100],"global":[103],"collective":[107],"evaluate":[110],"case":[113],"studies":[114],"comparing":[115,130],"versus":[117,132],"approaches.":[119],"Results":[120],"show":[121],"learns":[124],"models":[126],"machines,":[129],"approaches":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}