{"id":"https://openalex.org/W4415179746","doi":"https://doi.org/10.23919/ecc65951.2025.11186937","title":"Partial Intention Encoding for Safe Multi-Agent Control via Deep Reinforcement Learning","display_name":"Partial Intention Encoding for Safe Multi-Agent Control via Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-24","ids":{"openalex":"https://openalex.org/W4415179746","doi":"https://doi.org/10.23919/ecc65951.2025.11186937"},"language":"en","primary_location":{"id":"doi:10.23919/ecc65951.2025.11186937","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc65951.2025.11186937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 European Control Conference (ECC)","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/A5086738988","display_name":"Turki Bin Mohaya","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Turki Bin Mohaya","raw_affiliation_strings":["University of Michigan,Department of Electrical Engineering and Computer Science,Ann Arbor,MI,USA,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical Engineering and Computer Science,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009028512","display_name":"Peter Seiler","orcid":"https://orcid.org/0000-0003-3423-1109"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Seiler","raw_affiliation_strings":["University of Michigan,Department of Electrical Engineering and Computer Science,Ann Arbor,MI,USA,48109"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Electrical Engineering and Computer Science,Ann Arbor,MI,USA,48109","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086738988"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15908976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9333000183105469,"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":0.9333000183105469,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8062000274658203},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6628000140190125},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6427000164985657},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6334999799728394},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.45329999923706055},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.4050999879837036},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38429999351501465}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8062000274658203},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6628000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6491000056266785},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6427000164985657},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6334999799728394},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4771000146865845},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.45329999923706055},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.36169999837875366},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3158000111579895},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28279998898506165},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/ecc65951.2025.11186937","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc65951.2025.11186937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 European Control Conference (ECC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W316935178","https://openalex.org/W1607353007","https://openalex.org/W1641379095","https://openalex.org/W1965455100","https://openalex.org/W1976195538","https://openalex.org/W2033118636","https://openalex.org/W2087340523","https://openalex.org/W2145339207","https://openalex.org/W2560504659","https://openalex.org/W2903709398","https://openalex.org/W2963625099","https://openalex.org/W2968945909","https://openalex.org/W3088218629","https://openalex.org/W3127561923","https://openalex.org/W3217694967","https://openalex.org/W4240514091","https://openalex.org/W4291364848","https://openalex.org/W4309299196","https://openalex.org/W4387917771","https://openalex.org/W4394998532"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"vehicles":[1,29],"can":[2],"improve":[3],"urban":[4],"traffic":[5],"safety":[6,96],"and":[7,11,91,97,115],"efficiency.":[8],"Nevertheless,":[9],"safely":[10],"efficiently":[12],"operating":[13],"them":[14],"is":[15,80],"an":[16,106],"ongoing":[17],"research":[18],"problem.":[19],"This":[20,99],"paper":[21],"specifically":[22],"studies":[23],"the":[24,35,57,62,67,77],"task":[25],"of":[26,69,73],"navigating":[27],"autonomous":[28],"through":[30,56],"unsignalized":[31],"intersections.":[32],"We":[33],"model":[34],"system":[36],"as":[37],"a":[38,70],"Decentralized":[39,45],"Partially":[40],"Observable":[41],"Markov":[42],"Decision":[43],"Process.":[44],"algorithms":[46],"for":[47],"each":[48],"vehicle":[49],"are":[50],"trained":[51],"using":[52],"deep":[53],"reinforcement":[54],"learning":[55],"QMIX":[58,63],"method.":[59],"Building":[60],"upon":[61],"approach,":[64],"we":[65],"encode":[66],"intentions":[68],"selected":[71],"number":[72],"neighboring":[74],"vehicles.":[75],"Moreover,":[76],"reward":[78],"function":[79],"designed":[81],"to":[82,105],"combine":[83],"both":[84],"individual":[85],"performance":[86,103],"(i.e.,":[87],"fuel":[88],"consumption,":[89],"speed,":[90,114],"trip":[92],"completion)":[93],"with":[94],"global":[95],"fairness.":[98],"work":[100],"shows":[101],"improved":[102],"compared":[104],"existing":[107],"conventional":[108],"driving":[109,113],"algorithm":[110],"in":[111],"reward,":[112],"safety.":[116]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-15T00:00:00"}