{"id":"https://openalex.org/W4391528779","doi":"https://doi.org/10.1109/mrs60187.2023.10416789","title":"Entropy Maximization in High Dimensional Multiagent State Spaces","display_name":"Entropy Maximization in High Dimensional Multiagent State Spaces","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4391528779","doi":"https://doi.org/10.1109/mrs60187.2023.10416789"},"language":"en","primary_location":{"id":"doi:10.1109/mrs60187.2023.10416789","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mrs60187.2023.10416789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Multi-Robot and Multi-Agent Systems (MRS)","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/A5083987064","display_name":"Ayhan Alp Aydeniz","orcid":"https://orcid.org/0000-0001-6279-9266"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayhan Alp Aydeniz","raw_affiliation_strings":["Oregon State University,Collaborative Robotics and Intelligent Systems Institute,Corvallis,Oregon,USA","Collaborative Robotics and Intelligent Systems Institute, Oregon State University, Corvallis, Oregon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University,Collaborative Robotics and Intelligent Systems Institute,Corvallis,Oregon,USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Collaborative Robotics and Intelligent Systems Institute, Oregon State University, Corvallis, Oregon, USA","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058298540","display_name":"Enrico Marchesini","orcid":"https://orcid.org/0000-0003-1858-7279"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enrico Marchesini","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information & Decision Systems,Cambridge,Massachusetts,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information & Decision Systems,Cambridge,Massachusetts,USA","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029561177","display_name":"Robert Loftin","orcid":"https://orcid.org/0000-0001-9888-178X"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert Loftin","raw_affiliation_strings":["University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","Department of Computer Science, University of Sheffield, Sheffield, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sheffield,Department of Computer Science,Sheffield,United Kingdom","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084748531","display_name":"Kagan Tumer","orcid":"https://orcid.org/0009-0007-3809-7257"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kagan Tumer","raw_affiliation_strings":["Oregon State University,Collaborative Robotics and Intelligent Systems Institute,Corvallis,Oregon,USA","Collaborative Robotics and Intelligent Systems Institute, Oregon State University, Corvallis, Oregon, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University,Collaborative Robotics and Intelligent Systems Institute,Corvallis,Oregon,USA","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Collaborative Robotics and Intelligent Systems Institute, Oregon State University, Corvallis, Oregon, USA","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19796718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"92","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9822999835014343,"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/T10320","display_name":"Neural Networks and Applications","score":0.972599983215332,"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":0.6213019490242004},{"id":"https://openalex.org/keywords/entropy-maximization","display_name":"Entropy maximization","score":0.6108291745185852},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5614566802978516},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5458782315254211},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4433029294013977},{"id":"https://openalex.org/keywords/utility-maximization","display_name":"Utility maximization","score":0.4296499788761139},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4133497476577759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3249640464782715},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.24213668704032898},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23686620593070984},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19957175850868225},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.19089865684509277},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.13310733437538147},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08510816097259521},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.07952103018760681}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6213019490242004},{"id":"https://openalex.org/C127233936","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Entropy maximization","level":3,"score":0.6108291745185852},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5614566802978516},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5458782315254211},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4433029294013977},{"id":"https://openalex.org/C2985793214","wikidata":"https://www.wikidata.org/wiki/Q3274096","display_name":"Utility maximization","level":2,"score":0.4296499788761139},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4133497476577759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3249640464782715},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24213668704032898},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23686620593070984},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19957175850868225},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.19089865684509277},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.13310733437538147},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08510816097259521},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.07952103018760681}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mrs60187.2023.10416789","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mrs60187.2023.10416789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Symposium on Multi-Robot and Multi-Agent Systems (MRS)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:237269","is_oa":false,"landing_page_url":"https://orcid.org/0000-0001-9888-178X>","pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W135283623","https://openalex.org/W779494576","https://openalex.org/W1603022299","https://openalex.org/W1995875735","https://openalex.org/W2089943482","https://openalex.org/W2118688707","https://openalex.org/W2140332127","https://openalex.org/W2161061197","https://openalex.org/W2336509789","https://openalex.org/W2417786368","https://openalex.org/W2539402368","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2913756371","https://openalex.org/W2914261249","https://openalex.org/W2949475445","https://openalex.org/W2950794298","https://openalex.org/W2951799422","https://openalex.org/W2952465248","https://openalex.org/W2953326529","https://openalex.org/W2963276097","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W3172461472","https://openalex.org/W3173335063","https://openalex.org/W3209213092","https://openalex.org/W3214229832","https://openalex.org/W4200342431","https://openalex.org/W4210249822","https://openalex.org/W4226429284","https://openalex.org/W4283793632","https://openalex.org/W4285102394","https://openalex.org/W4285805494","https://openalex.org/W4287867830","https://openalex.org/W4297804636","https://openalex.org/W4383108795","https://openalex.org/W4384024651","https://openalex.org/W6622487243","https://openalex.org/W6674657456","https://openalex.org/W6677477928","https://openalex.org/W6682484022","https://openalex.org/W6703140735","https://openalex.org/W6716474083","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6735865323","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748271565","https://openalex.org/W6748603076","https://openalex.org/W6748839928","https://openalex.org/W6755903938","https://openalex.org/W6757058172","https://openalex.org/W6758978475","https://openalex.org/W6765240361","https://openalex.org/W6771807793","https://openalex.org/W6779884726","https://openalex.org/W6788085919","https://openalex.org/W6791110673","https://openalex.org/W6791194670","https://openalex.org/W6797434948","https://openalex.org/W6849907714","https://openalex.org/W6850449689"],"related_works":["https://openalex.org/W3102188974","https://openalex.org/W3004810941","https://openalex.org/W4287870705","https://openalex.org/W3121521771","https://openalex.org/W3199097846","https://openalex.org/W30823005","https://openalex.org/W624081655","https://openalex.org/W2393902186","https://openalex.org/W4388998647","https://openalex.org/W2267645079"],"abstract_inverted_index":{"Underwater":[0],"or":[1],"planetary":[2],"exploration":[3],"are":[4],"prime":[5],"examples":[6],"of":[7,42,87,120],"missions":[8],"that":[9,155],"can":[10],"benefit":[11],"from":[12],"autonomous":[13],"agents":[14,32,52,101,160],"working":[15],"together.":[16],"However,":[17],"discovering":[18],"effective":[19,78,139],"team-level":[20],"behaviors":[21,165],"(i.e.,":[22,73],"coordinated":[23],"joint":[24,152],"actions)":[25],"is":[26],"challenging":[27],"in":[28,140,146,166],"these":[29],"domains":[30],"as":[31,65,79],"typically":[33],"receive":[34],"a":[35,84],"sparse":[36],"reward":[37],"(zero-or":[38],"constant-for":[39],"the":[40,43,59,66,111,121,133],"majority":[41],"interactions).":[44],"To":[45],"address":[46],"this":[47,90],"issue,":[48],"intrinsic":[49,71,122],"rewards":[50,106,158,174],"encourage":[51],"to":[53,57,109,124,137,161],"explore":[54,102],"diverse":[55,85],"policies":[56],"visit":[58],"state":[60,68,94,134,143],"space":[61,69],"more":[62],"effectively.":[63],"Unfortunately,":[64],"agents\u2019":[67],"grows,":[70],"reward-based":[72],"curiosity)":[74],"approaches":[75],"become":[76],"less":[77],"they":[80],"cannot":[81],"effectively":[82],"distinguish":[83],"set":[86],"states.":[88],"In":[89],"direction,":[91],"we":[92],"introduce":[93],"entropy":[95,135],"maximization":[96],"for":[97],"multiagent":[98],"learning":[99],"where":[100,170],"using":[103],"local":[104,126,156],"(dense)":[105],"and":[107,127],"learn":[108],"solve":[110],"coordination":[112],"task":[113],"by":[114],"leveraging":[115],"global":[116,128],"(sparse)":[117],"rewards.":[118],"Because":[119],"ability":[123],"balance":[125],"rewards,":[129],"our":[130],"approach":[131],"enables":[132],"function":[136],"remain":[138],"high":[141,167],"dimensional":[142,168],"spaces.":[144],"Experiments":[145],"tightly":[147],"coupled":[148],"tasks":[149],"requiring":[150],"complex":[151],"actions,":[153],"show":[154],"entropy-based":[157],"enable":[159],"discover":[162],"successful":[163],"team":[164],"spaces":[169],"previous":[171],"hand-tuned":[172],"count-based":[173],"fail.":[175]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}