{"id":"https://openalex.org/W4411599507","doi":"https://doi.org/10.1109/tro.2025.3582836","title":"Physics-Informed Multiagent Reinforcement Learning for Distributed Multirobot Problems","display_name":"Physics-Informed Multiagent Reinforcement Learning for Distributed Multirobot Problems","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411599507","doi":"https://doi.org/10.1109/tro.2025.3582836"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2025.3582836","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3582836","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tro.2025.3582836","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102919228","display_name":"Eduardo Sebasti\u00e1n","orcid":"https://orcid.org/0000-0001-9671-4056"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduardo Sebasti\u00e1n","raw_affiliation_strings":["Department of Computer Science and Systems Engineering (DIIS) and the Engineering Research Institute of Aragon (I3A), Universidad de Zaragoza, Zaragoza, Spain","DIIS - I3A, Universidad de Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9671-4056","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Systems Engineering (DIIS) and the Engineering Research Institute of Aragon (I3A), Universidad de Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]},{"raw_affiliation_string":"DIIS - I3A, Universidad de Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041269823","display_name":"Thai Duong","orcid":"https://orcid.org/0000-0002-8115-8330"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thai Duong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8115-8330","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066400889","display_name":"Nikolay Atanasov","orcid":"https://orcid.org/0000-0003-0272-7580"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolay Atanasov","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0272-7580","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010149148","display_name":"Eduardo Montijano","orcid":"https://orcid.org/0000-0002-5176-3767"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduardo Montijano","raw_affiliation_strings":["Department of Computer Science and Systems Engineering (DIIS) and the Engineering Research Institute of Aragon (I3A), Universidad de Zaragoza, Zaragoza, Spain","DIIS - I3A, Universidad de Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0002-5176-3767","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Systems Engineering (DIIS) and the Engineering Research Institute of Aragon (I3A), Universidad de Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]},{"raw_affiliation_string":"DIIS - I3A, Universidad de Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052842220","display_name":"Carlos Sag\u00fc\u00e9s","orcid":"https://orcid.org/0000-0002-3032-954X"},"institutions":[{"id":"https://openalex.org/I255234318","display_name":"Universidad de Zaragoza","ror":"https://ror.org/012a91z28","country_code":"ES","type":"education","lineage":["https://openalex.org/I255234318"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Carlos Sag\u00fc\u00e9s","raw_affiliation_strings":["Department of Computer Science and Systems Engineering (DIIS) and the Engineering Research Institute of Aragon (I3A), Universidad de Zaragoza, Zaragoza, Spain","DIIS - I3A, Universidad de Zaragoza, Spain"],"raw_orcid":"https://orcid.org/0000-0002-3032-954X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Systems Engineering (DIIS) and the Engineering Research Institute of Aragon (I3A), Universidad de Zaragoza, Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]},{"raw_affiliation_string":"DIIS - I3A, Universidad de Zaragoza, Spain","institution_ids":["https://openalex.org/I255234318"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.3465,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99167736,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"41","issue":null,"first_page":"4499","last_page":"4517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9991000294685364,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7392753958702087},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6171154379844666},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.45903515815734863},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.4310087561607361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42455947399139404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4164809584617615},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3516038656234741},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34173503518104553},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3357933759689331}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7392753958702087},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6171154379844666},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.45903515815734863},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.4310087561607361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42455947399139404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4164809584617615},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3516038656234741},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34173503518104553},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3357933759689331}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tro.2025.3582836","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3582836","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},{"id":"pmh:oai:zaguan.unizar.es:162315","is_oa":true,"landing_page_url":"http://zaguan.unizar.es/record/162315","pdf_url":null,"source":{"id":"https://openalex.org/S4306401812","display_name":"Zaguan (University of Zaragoza Repository)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I255234318","host_organization_name":"Universidad de Zaragoza","host_organization_lineage":["https://openalex.org/I255234318"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1109/tro.2025.3582836","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tro.2025.3582836","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1625642672","display_name":null,"funder_award_id":"N62909-24-1-2081","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G479547996","display_name":null,"funder_award_id":"N00014-23-1-2353","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6834828634","display_name":null,"funder_award_id":"PID2021-124137OB-I00","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6966210806","display_name":null,"funder_award_id":"PID2021-125514NB-I00","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7314356867","display_name":null,"funder_award_id":"NSF CCF-2402689","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8788738189","display_name":null,"funder_award_id":"TED2021-130224B-I00","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"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":99,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1192553058","https://openalex.org/W1562003885","https://openalex.org/W1572260348","https://openalex.org/W1639167632","https://openalex.org/W2072770984","https://openalex.org/W2096145798","https://openalex.org/W2096876511","https://openalex.org/W2108892923","https://openalex.org/W2131956831","https://openalex.org/W2158782408","https://openalex.org/W2396783599","https://openalex.org/W2602275733","https://openalex.org/W2749807327","https://openalex.org/W2857457978","https://openalex.org/W2904246096","https://openalex.org/W2907537824","https://openalex.org/W2913845934","https://openalex.org/W2949464762","https://openalex.org/W2951360122","https://openalex.org/W2962727772","https://openalex.org/W2963821308","https://openalex.org/W2964138223","https://openalex.org/W2968526727","https://openalex.org/W2973229164","https://openalex.org/W2992032464","https://openalex.org/W2998212266","https://openalex.org/W3003456989","https://openalex.org/W3008967682","https://openalex.org/W3090254537","https://openalex.org/W3091076647","https://openalex.org/W3099689767","https://openalex.org/W3109907338","https://openalex.org/W3130046404","https://openalex.org/W3135699331","https://openalex.org/W3156295478","https://openalex.org/W3158900575","https://openalex.org/W3161939764","https://openalex.org/W3163926178","https://openalex.org/W3165062653","https://openalex.org/W3166401044","https://openalex.org/W3205823236","https://openalex.org/W3207676534","https://openalex.org/W3209876175","https://openalex.org/W3209969885","https://openalex.org/W4221145105","https://openalex.org/W4226481925","https://openalex.org/W4237637693","https://openalex.org/W4282007775","https://openalex.org/W4285201047","https://openalex.org/W4286748781","https://openalex.org/W4288039037","https://openalex.org/W4299802797","https://openalex.org/W4308033457","https://openalex.org/W4311723471","https://openalex.org/W4320930577","https://openalex.org/W4378945674","https://openalex.org/W4382119054","https://openalex.org/W4382931248","https://openalex.org/W4382935812","https://openalex.org/W4383108483","https://openalex.org/W4383108785","https://openalex.org/W4383108791","https://openalex.org/W4385245566","https://openalex.org/W4385482750","https://openalex.org/W4386001266","https://openalex.org/W4388579659","https://openalex.org/W4388918867","https://openalex.org/W4389363807","https://openalex.org/W4389667356","https://openalex.org/W4391405925","https://openalex.org/W4401416687","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6638908295","https://openalex.org/W6738796088","https://openalex.org/W6743756900","https://openalex.org/W6746023985","https://openalex.org/W6747473740","https://openalex.org/W6747941106","https://openalex.org/W6755069753","https://openalex.org/W6757592117","https://openalex.org/W6757797181","https://openalex.org/W6760725535","https://openalex.org/W6763484891","https://openalex.org/W6766224423","https://openalex.org/W6769609827","https://openalex.org/W6771232374","https://openalex.org/W6771904302","https://openalex.org/W6795908048","https://openalex.org/W6797920683","https://openalex.org/W6802002411","https://openalex.org/W6811352066","https://openalex.org/W6839220874","https://openalex.org/W6840380725","https://openalex.org/W6847053823","https://openalex.org/W6847213728","https://openalex.org/W6851077459","https://openalex.org/W6859368398"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"The":[0],"networked":[1,103],"nature":[2,104],"of":[3,11,24,69,97,105,160,173,218,248],"multi-robot":[4,59,168,179],"systems":[5,100],"presents":[6],"challenges":[7],"in":[8,42,166,183,232],"the":[9,33,71,90,102,128,150,158,171,174,204,216,233],"context":[10],"multi-agent":[12],"reinforcement":[13,52,137,180],"learning.":[14],"Centralized":[15],"control":[16,28,60,145],"policies":[17,29,61],"do":[18,30],"not":[19,31],"scale":[20],"with":[21,206],"increasing":[22],"numbers":[23],"robots,":[25,38],"whereas":[26],"independent":[27],"exploit":[32],"information":[34,73,123],"provided":[35],"by":[36,141],"other":[37],"exhibiting":[39],"poor":[40],"performance":[41,190],"cooperative-competitive":[43],"tasks.":[44],"In":[45],"this":[46],"work":[47],"we":[48,132],"propose":[49],"a":[50,86,115,134],"physics-informed":[51],"learning":[53,138,181],"approach":[54,78,227],"able":[55,119],"to":[56,74,113,120,196],"learn":[57],"distributed":[58],"that":[62],"are":[63],"both":[64],"scalable":[65],"and":[66,101,244],"make":[67],"use":[68],"all":[70],"available":[72],"each":[75,125],"robot.":[76],"Our":[77],"has":[79],"three":[80],"key":[81],"characteristics.":[82],"First,":[83],"it":[84,110],"imposes":[85],"port-Hamiltonian":[87,144],"structure":[88],"on":[89,228],"policy":[91,117],"representation,":[92],"respecting":[93],"energy":[94],"conservation":[95],"properties":[96],"physical":[98],"robot":[99,106,126,207],"team":[107],"interactions.":[108],"Second,":[109],"uses":[111],"self-attention":[112,143],"ensure":[114],"sparse":[116],"representation":[118],"handle":[121],"time-varying":[122],"at":[124,220],"from":[127],"interaction":[129],"graph.":[130],"Third,":[131],"present":[133],"soft":[135],"actor-critic":[136],"algorithm":[139],"parameterized":[140],"our":[142,226],"policy,":[146],"which":[147],"accounts":[148],"for":[149],"correlation":[151],"among":[152],"robots":[153,219,231],"during":[154],"training":[155,221],"while":[156,185],"overcoming":[157],"need":[159],"value":[161],"function":[162],"factorization.":[163],"Extensive":[164],"simulations":[165],"different":[167],"scenarios":[169],"demonstrate":[170],"success":[172],"proposed":[175],"approach,":[176],"surpassing":[177],"previous":[178],"solutions":[182],"scalability,":[184],"achieving":[186],"similar":[187],"or":[188],"superior":[189],"(with":[191],"averaged":[192],"cumulative":[193],"reward":[194],"up":[195],"<inline-formula":[197,209],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[198,210],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[199,211],"notation=\"LaTeX\">$\\times":[200,212],"2$</tex-math></inline-formula>":[201],"greater":[202],"than":[203,215],"state-of-the-art":[205],"teams":[208],"6$</tex-math></inline-formula>":[213],"larger":[214],"number":[217,247],"time).":[222],"We":[223],"also":[224],"validate":[225],"multiple":[229],"real":[230],"Georgia":[234],"Tech":[235],"Robotarium":[236],"under":[237],"imperfect":[238],"communication,":[239],"demonstrating":[240],"zero-shot":[241],"sim-to-real":[242],"transfer":[243],"scalability":[245],"across":[246],"robots.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}