{"id":"https://openalex.org/W7161261974","doi":"https://doi.org/10.1613/jair.1.20494","title":"Safe Learning of Multi-Agent Action Models from Concurrent Joint Action Observations","display_name":"Safe Learning of Multi-Agent Action Models from Concurrent Joint Action Observations","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161261974","doi":"https://doi.org/10.1613/jair.1.20494"},"language":null,"primary_location":{"id":"doi:10.1613/jair.1.20494","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.20494","pdf_url":"https://www.jair.org/index.php/jair/article/download/20494/27304","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jair.org/index.php/jair/article/download/20494/27304","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087931133","display_name":"Argaman Mordoch","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Argaman Mordoch","raw_affiliation_strings":["Ben Gurion University"],"raw_orcid":"https://orcid.org/0000-0003-3502-1461","affiliations":[{"raw_affiliation_string":"Ben Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136255398","display_name":"Ori Karat","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ori Karat","raw_affiliation_strings":["Ben Gurion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136269692","display_name":"Lea Shmilovich","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Lea Shmilovich","raw_affiliation_strings":["Ben Gurion University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ben Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098974818","display_name":"Yarin Benyamin","orcid":null},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yarin Benyamin","raw_affiliation_strings":["Ben Gurion University"],"raw_orcid":"https://orcid.org/0009-0008-7427-6380","affiliations":[{"raw_affiliation_string":"Ben Gurion University","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064954992","display_name":"Brendan Juba","orcid":"https://orcid.org/0000-0001-6542-833X"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brendan Juba","raw_affiliation_strings":["Washington University in St. Louis"],"raw_orcid":"https://orcid.org/0000-0001-6542-833X","affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085970582","display_name":"Roni Stern","orcid":"https://orcid.org/0000-0003-0043-8179"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roni Stern","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0043-8179","affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48462131,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"86","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.6193000078201294,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.6193000078201294,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.21850000321865082,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.024900000542402267,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/action","display_name":"Action (physics)","score":0.6061000227928162},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.5543000102043152},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48429998755455017},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.375},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.35350000858306885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177000284194946},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.5543000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5475999712944031},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4731000065803528},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.375},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3179999887943268},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1613/jair.1.20494","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.20494","pdf_url":"https://www.jair.org/index.php/jair/article/download/20494/27304","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1613/jair.1.20494","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.20494","pdf_url":"https://www.jair.org/index.php/jair/article/download/20494/27304","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2931886712","display_name":null,"funder_award_id":"1238/23","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"},{"id":"https://openalex.org/G6471319493","display_name":"CAREER: Relational generalization in integrated learning and reasoning","funder_award_id":"1942336","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7161261974.pdf","grobid_xml":"https://content.openalex.org/works/W7161261974.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Background:":[0],"Multi-Agent":[1,23,163,221],"Planning":[2,24],"(MAP)":[3],"involves":[4],"coordinating":[5],"the":[6,22,102,110,119,148,152,155,196,216,232,243,307,313],"actions":[7],"of":[8,151,200,205,207,218,306,317],"multiple":[9],"autonomous":[10],"agents":[11,153],"to":[12,38,109,154,176],"achieve":[13,260],"shared":[14],"objectives.":[15],"A":[16],"prevalent":[17],"formalism":[18],"for":[19,95,126,134,246],"MAP":[20,228],"is":[21,51,131,295],"Domain":[25],"Definition":[26],"Language":[27],"(MA-PDDL).":[28],"While":[29,292],"effective,":[30],"existing":[31],"MA-PDDL":[32,135,320],"solvers":[33],"typically":[34],"require":[35],"complete":[36],"access":[37],"agents\u2019":[39,67],"action":[40,68,113,171,185,249,321],"models\u2014specifically":[41],"their":[42,293],"preconditions":[43,197],"and":[44,198,220,225,281,289,331],"effects.":[45,157],"However,":[46,129],"manually":[47],"creating":[48],"these":[49],"models":[50,69,75,250,322],"often":[52],"intractable,":[53],"requiring":[54],"exhaustive":[55],"domain":[56,229],"expertise.":[57],"Objectives:":[58],"This":[59],"work":[60],"explores":[61],"an":[62],"alternative":[63],"approach:":[64],"automatically":[65],"learning":[66,173,247,318],"from":[70,215,323],"observed":[71,156],"transitions.":[72],"Since":[73],"learned":[74,103],"may":[76,275],"be":[77],"inaccurate,":[78],"planning":[79,336],"with":[80,107],"them":[81],"can":[82],"yield":[83],"invalid":[84],"or":[85],"non-executable":[86],"sequences.":[87],"To":[88,158],"mitigate":[89],"this,":[90,160],"we":[91,161,189],"formalize":[92],"a":[93,169,226,238],"requirement":[94],"safety,":[96],"ensuring":[97],"that":[98,256],"plans":[99],"generated":[100],"via":[101],"model":[104,172],"remain":[105,187],"sound":[106],"respect":[108],"real":[111],"unknown":[112],"model.":[114],"Methods:":[115],"Previous":[116],"research":[117],"introduced":[118],"Safe":[120,164],"Action":[121,165],"Model":[122,166],"Learning":[123,167],"(SAM)":[124],"algorithm":[125,174],"single-agent":[127],"domains.":[128,309],"SAM":[130],"not":[132,259],"suitable":[133],"environments":[136],"where":[137,183],"observations":[138],"include":[139],"concurrently":[140,324],"executed":[141,325],"actions,":[142,326],"since":[143],"it":[144],"cannot":[145],"naturally":[146],"disambiguate":[147],"individual":[149,184],"contributions":[150],"address":[159],"introduce":[162],"(MA-SAM),":[168],"safe":[170,248,319],"designed":[175],"handle":[177],"concurrent":[178,203],"multi-agent":[179,252],"observations.":[180],"For":[181],"scenarios":[182],"effects":[186,199],"ambiguous,":[188],"further":[190],"propose":[191],"MA-SAM+":[192,282,300],",":[193],"which":[194,271],"learns":[195],"macro-actions":[201],"representing":[202],"execution":[204],"subsets":[206],"actions.":[208],"We":[209,236,254,311],"evaluate":[210],"both":[211,279,328],"algorithms":[212,315],"on":[213,242],"domains":[214],"Competition":[217],"Distributed":[219],"Planners":[222],"(CoDMAP)":[223],"benchmarks":[224,337],"novel":[227],"inspired":[230],"by":[231],"game":[233],"Overcooked.":[234],"Results:":[235],"establish":[237],"theoretical":[239,329],"lower":[240,262],"bound":[241,263],"sample":[244,273],"complexity":[245,274],"in":[251,264,287,297,304],"settings.":[253],"prove":[255],"MA-SAM":[257,280,303],"does":[258],"this":[261],"all":[265],"cases,":[266],"identifying":[267],"specific":[268],"conditions":[269],"under":[270],"its":[272],"become":[276],"unbounded.":[277],"Empirically,":[278],"significantly":[283],"outperform":[284],"SAM-based":[285],"baselines":[286],"coverage":[288],"applicability":[290],"rates.":[291],"performance":[294],"comparable":[296],"many":[298],"settings,":[299],"highly":[301],"outperforms":[302],"some":[305],"evaluated":[308],"Conclusions:":[310],"present":[312],"first":[314],"capable":[316],"providing":[327],"foundations":[330],"empirical":[332],"validation":[333],"across":[334],"diverse":[335]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-05-16T00:00:00"}