{"id":"https://openalex.org/W4387914238","doi":"https://doi.org/10.1109/codit58514.2023.10284342","title":"Multi-Agent Reinforcement Learning with Epistemic Priors","display_name":"Multi-Agent Reinforcement Learning with Epistemic Priors","publication_year":2023,"publication_date":"2023-07-03","ids":{"openalex":"https://openalex.org/W4387914238","doi":"https://doi.org/10.1109/codit58514.2023.10284342"},"language":"en","primary_location":{"id":"doi:10.1109/codit58514.2023.10284342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit58514.2023.10284342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)","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/A5035272943","display_name":"Thayne T. Walker","orcid":null},"institutions":[{"id":"https://openalex.org/I131651094","display_name":"University of Denver","ror":"https://ror.org/04w7skc03","country_code":"US","type":"education","lineage":["https://openalex.org/I131651094"]},{"id":"https://openalex.org/I183804699","display_name":"Lockheed Martin (Canada)","ror":"https://ror.org/00rs6n938","country_code":"CA","type":"company","lineage":["https://openalex.org/I1287521167","https://openalex.org/I183804699"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Thayne T. Walker","raw_affiliation_strings":["Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","Department of Computer Science, University of Denver"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","institution_ids":["https://openalex.org/I183804699"]},{"raw_affiliation_string":"Department of Computer Science, University of Denver","institution_ids":["https://openalex.org/I131651094"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021695968","display_name":"Jaime S. Ide","orcid":"https://orcid.org/0000-0002-7223-1102"},"institutions":[{"id":"https://openalex.org/I183804699","display_name":"Lockheed Martin (Canada)","ror":"https://ror.org/00rs6n938","country_code":"CA","type":"company","lineage":["https://openalex.org/I1287521167","https://openalex.org/I183804699"]},{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Jaime S. Ide","raw_affiliation_strings":["Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","Department of Psychiatry, Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","institution_ids":["https://openalex.org/I183804699"]},{"raw_affiliation_string":"Department of Psychiatry, Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065357431","display_name":"Minkyu Choi","orcid":"https://orcid.org/0000-0001-5872-6478"},"institutions":[{"id":"https://openalex.org/I183804699","display_name":"Lockheed Martin (Canada)","ror":"https://ror.org/00rs6n938","country_code":"CA","type":"company","lineage":["https://openalex.org/I1287521167","https://openalex.org/I183804699"]},{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Minkyu Choi","raw_affiliation_strings":["Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","institution_ids":["https://openalex.org/I183804699"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013142527","display_name":"Michael J. Guarino","orcid":null},"institutions":[{"id":"https://openalex.org/I183804699","display_name":"Lockheed Martin (Canada)","ror":"https://ror.org/00rs6n938","country_code":"CA","type":"company","lineage":["https://openalex.org/I1287521167","https://openalex.org/I183804699"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Michael Guarino","raw_affiliation_strings":["Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","institution_ids":["https://openalex.org/I183804699"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056176118","display_name":"Kevin Alcedo","orcid":null},"institutions":[{"id":"https://openalex.org/I183804699","display_name":"Lockheed Martin (Canada)","ror":"https://ror.org/00rs6n938","country_code":"CA","type":"company","lineage":["https://openalex.org/I1287521167","https://openalex.org/I183804699"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kevin Alcedo","raw_affiliation_strings":["Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lockheed Martin Artificial Intelligence Center (LAIC), Applied AI Team","institution_ids":["https://openalex.org/I183804699"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4895,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71623842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2514","last_page":"2518"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9950000047683716,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9937999844551086,"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/unobservable","display_name":"Unobservable","score":0.9261825084686279},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8061153888702393},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.7208912372589111},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6789305210113525},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.47228437662124634},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.4313918948173523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4204273819923401},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3694630265235901},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34528830647468567},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.20582228899002075},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15746617317199707}],"concepts":[{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.9261825084686279},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8061153888702393},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7208912372589111},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6789305210113525},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.47228437662124634},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.4313918948173523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4204273819923401},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3694630265235901},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34528830647468567},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.20582228899002075},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15746617317199707},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit58514.2023.10284342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit58514.2023.10284342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1599431202","https://openalex.org/W1641379095","https://openalex.org/W1998176101","https://openalex.org/W2088956500","https://openalex.org/W2141538250","https://openalex.org/W2163854321","https://openalex.org/W2168359464","https://openalex.org/W2188435450","https://openalex.org/W2395575420","https://openalex.org/W2396783599","https://openalex.org/W2529466265","https://openalex.org/W2592114483","https://openalex.org/W2626637010","https://openalex.org/W2758442112","https://openalex.org/W2964251366","https://openalex.org/W2998030398","https://openalex.org/W3120133621","https://openalex.org/W3198778749","https://openalex.org/W4286748781","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6635772738","https://openalex.org/W6712181171","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6748910126","https://openalex.org/W6749304979","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2614563012","https://openalex.org/W2149686805","https://openalex.org/W4294689033","https://openalex.org/W4226462367","https://openalex.org/W1978158123","https://openalex.org/W2967463586","https://openalex.org/W2082642870","https://openalex.org/W2378270039","https://openalex.org/W4246201196"],"abstract_inverted_index":{"It":[0],"is":[1],"important":[2],"for":[3,43],"autonomous":[4],"multi-agent":[5,36],"teams":[6],"to":[7,48,77,98],"coordinate":[8],"actions":[9],"so":[10],"that":[11,89],"collaborative":[12],"goals":[13],"can":[14],"be":[15,99],"achieved":[16,100],"efficiently":[17],"without":[18],"conflicts.":[19],"Practical":[20],"issues":[21],"in":[22,46],"multi-agent,":[23],"real-time":[24],"systems":[25],"are":[26,85],"limited":[27],"sensing":[28,104],"and":[29,105],"communication":[30,107],"capabilities.":[31],"A":[32],"significant":[33],"number":[34],"of":[35,80,96],"algorithms":[37],"rely":[38],"on":[39],"accurate":[40],"state":[41],"information":[42],"all":[44],"agents":[45,72],"order":[47],"effectively":[49],"coordinate.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"an":[56],"approach":[57],"called":[58],"Reinforcement":[59],"Learning":[60],"with":[61,101],"Epistemic":[62],"Priors":[63],"(MARL-EP).":[64],"MARL-EP":[65,90],"incorporates":[66],"a":[67,92],"shared":[68],"mental":[69],"model":[70],"between":[71,108],"by":[73],"leveraging":[74],"epistemic":[75],"estimation":[76],"infer":[78],"portions":[79],"the":[81],"obser-vation":[82],"space":[83],"which":[84],"unobservable.":[86],"We":[87],"show":[88],"allows":[91],"very":[93],"high":[94],"level":[95],"coordination":[97],"severely":[102],"impaired":[103],"zero":[106],"agents.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}