{"id":"https://openalex.org/W7223053946","doi":"https://doi.org/10.48550/arxiv.2610.25113","title":"A learner-free swarm reaches the explore-exploit equilibrium: A self-organized attractor approximating the reinforcement-learning solution","display_name":"A learner-free swarm reaches the explore-exploit equilibrium: A self-organized attractor approximating the reinforcement-learning solution","publication_year":2026,"publication_date":"2026-10-18","ids":{"openalex":"https://openalex.org/W7223053946","doi":"https://doi.org/10.48550/arxiv.2610.25113"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.25113","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25113","pdf_url":"https://arxiv.org/pdf/2610.25113","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.25113","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059553482","display_name":"Galen Wilkerson","orcid":"https://orcid.org/0000-0002-7957-5821","observed_orcids":["https://orcid.org/0000-0002-7957-5821"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wilkerson, Galen J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5059553482"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5278000235557556,"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":0.5278000235557556,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.18080000579357147,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.093299999833107,"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/explore-exploit-trade-off","display_name":"explore-exploit trade-off","score":0.9900000095367432},{"id":"https://openalex.org/keywords/ideal-free-distribution","display_name":"ideal free distribution","score":0.7419999837875366},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7699999809265137},{"id":"https://openalex.org/keywords/congestion-games","display_name":"congestion games","score":0.6819999814033508},{"id":"https://openalex.org/keywords/self-organization","display_name":"self-organization","score":0.781000018119812},{"id":"https://openalex.org/keywords/attractor-dynamics","display_name":"attractor dynamics","score":0.6570000052452087},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.40400001406669617},{"id":"https://openalex.org/keywords/multi-agent-resource-allocation","display_name":"multi-agent resource allocation","score":0.6269999742507935},{"id":"https://openalex.org/keywords/levy-flight","display_name":"L\u00e9vy flight","score":0.5490000247955322},{"id":"https://openalex.org/keywords/graph-message-passing","display_name":"graph message passing","score":0.5440000295639038},{"id":"https://openalex.org/keywords/centralized-critic","display_name":"centralized critic","score":0.5709999799728394},{"id":"https://openalex.org/keywords/swarm-intelligence","display_name":"swarm intelligence","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.8080000281333923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151000261306763},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5286999940872192},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5156999826431274},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4876999855041504},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4523000121116638},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953000009059906},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.3880999982357025},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C165287380","wikidata":"https://www.wikidata.org/wiki/Q2916569","display_name":"Foraging","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.25113","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25113","pdf_url":"https://arxiv.org/pdf/2610.25113","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.25113","doi":"https://doi.org/10.48550/arxiv.2610.25113","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.25113","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.25113","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25113","pdf_url":"https://arxiv.org/pdf/2610.25113","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223053946.pdf","grobid_xml":"https://content.openalex.org/works/W7223053946.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W7083318975"],"related_works":["https://openalex.org/W3202329902","https://openalex.org/W7161941346","https://openalex.org/W6964577119","https://openalex.org/W4413209785","https://openalex.org/W4406625510","https://openalex.org/W4392305667","https://openalex.org/W4402264525","https://openalex.org/W7023970541","https://openalex.org/W3037618737","https://openalex.org/W7128122566"],"abstract_inverted_index":{"The":[0,120,137],"explore-exploit":[1],"trade-off":[2],"is":[3,18,123,222],"the":[4,16,28,32,47,109,116,125,128,131,135,151,176,180,187,201,216,270,287],"core":[5],"problem":[6,129],"of":[7,35,49,111,127,211],"reinforcement":[8,121],"learning":[9,122,144],"(RL).":[10],"In":[11],"its":[12,81,147],"multi-agent,":[13],"resource-sharing":[14],"form":[15],"optimum":[17],"not":[19,134,150,238,257],"a":[20,36,42,53,92,95,105,163,239,246,265,275,277,280],"scalar-return":[21],"maximum":[22],"but":[23,149,261],"an":[24,212],"equilibrium":[25,34,51,141,271],"allocation":[26,132],"--":[27,56,66],"ideal-free":[29],"distribution":[30],"(IFD),":[31],"Nash":[33],"congestion":[37],"game.":[38],"We":[39,254],"show":[40],"that":[41,264],"minimal":[43,266],"foraging":[44],"swarm":[45,138,182],"reaches":[46,139,269],"shape":[48,148],"this":[50,140,252,256],"as":[52,104,258,262],"self-organized":[54],"attractor":[55],"foragers":[57],"in":[58,80,175],"proportion":[59],"to":[60,91,113],"resource":[61,221],"richness":[62],"(matching":[63],"slope":[64],"0.94)":[65],"with":[67],"no":[68,70,74],"learner,":[69,276],"trained":[71,174,281],"parameters,":[72],"and":[73,102,130,171,199,227,236],"payoff":[75],"or":[76,279],"reward":[77],"read":[78,255],"anywhere":[79],"dynamics.":[82],"Agents":[83],"explore":[84],"by":[85],"heavy-tailed":[86],"(Levy)":[87],"flights,":[88],"recruit":[89],"neighbours":[90],"discovery":[93],"through":[94],"threshold":[96],"cascade":[97],"on":[98],"their":[99],"proximity":[100],"network,":[101],"disperse":[103],"patch":[106],"crowds;":[107],"removing":[108],"coupling":[110],"recruitment":[112],"movement":[114],"collapses":[115],"matching":[117],"(slope":[118,195],"0.08).":[119],"at":[124,183,209,251],"level":[126],"reached,":[133],"micro-rule.":[136],"rather":[142],"than":[143,192],"it,":[145],"attaining":[146],"exact":[152],"equilibrium:":[153],"it":[154,250],"stays":[155],"measurably":[156],"exploitable":[157],"(Nash-gap":[158],"0.58":[159],"versus":[160],"~0.01":[161],"for":[162],"converged":[164],"learner).":[165],"Against":[166],"PPO":[167],"learners":[168],"(feedforward,":[169],"centralized-critic,":[170],"graph":[172],"message-passing)":[173],"same":[177],"sensing-limited":[178],"environment,":[179],"reward-free":[181],"zero":[184],"training":[185],"matches":[186],"IFD":[188],"gradient":[189],"more":[190,219],"faithfully":[191],"any":[193],"learner":[194,217],"~1":[196],"vs":[197,225],"0.69-0.91)":[198],"ties":[200],"best":[202],"learner's":[203],"harvest":[204],"where":[205,220],"clustered":[206],"(both":[207],"plateau":[208],"~0.80":[210],"oracle":[213],"ceiling),":[214],"while":[215],"collects":[218],"scarce":[223],"(0.33":[224],"0.22)":[226],"holds":[228],"tighter":[229],"per-capita":[230],"intake.":[231],"Learning":[232],"thus":[233],"buys":[234],"precision":[235],"transfer,":[237],"better":[240],"allocation;":[241],"neither":[242],"message":[243],"passing":[244],"nor":[245],"centralized":[247],"critic":[248],"exceeds":[249],"budget.":[253],"beating":[259],"RL,":[260],"evidence":[263],"swarm's":[267],"physics":[268],"RL":[272],"seeks":[273],"without":[274],"reward,":[278],"parameter.":[282],"A":[283],"companion":[284],"paper":[285],"develops":[286],"mechanism.":[288]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-21T00:00:00"}