{"id":"https://openalex.org/W3201333390","doi":null,"title":"Evolutionary Reinforcement Learning Dynamics with Irreducible Environmental Uncertainty.","display_name":"Evolutionary Reinforcement Learning Dynamics with Irreducible Environmental Uncertainty.","publication_year":2021,"publication_date":"2021-09-15","ids":{"openalex":"https://openalex.org/W3201333390","mag":"3201333390"},"language":"en","primary_location":{"id":"mag:3201333390","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2109.07259.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2109.07259.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047941384","display_name":"Wolfram Barfu\u00df","orcid":"https://orcid.org/0000-0002-9077-5242","observed_orcids":["https://orcid.org/0000-0002-9077-5242"]},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wolfram Barfu\u00df","raw_affiliation_strings":["University of T\u00fcbingen"],"raw_orcid":"https://orcid.org/0000-0002-9077-5242","affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014611168","display_name":"Richard P. Mann","orcid":"https://orcid.org/0000-0003-0701-1274","observed_orcids":["https://orcid.org/0000-0003-0701-1274","https://orcid.org/0000-0002-4749-2765"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Richard P. Mann","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0701-1274","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.6679999828338623,"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":0.6679999828338623,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.1881999969482422,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.060100000351667404,"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/evolutionary-reinforcement-learning","display_name":"evolutionary reinforcement learning","score":0.9679999947547913},{"id":"https://openalex.org/keywords/partial-observability","display_name":"partial observability","score":0.972000002861023},{"id":"https://openalex.org/keywords/social-dilemmas","display_name":"social dilemmas","score":0.9319999814033508},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.7620000243186951},{"id":"https://openalex.org/keywords/critical-slowing-down","display_name":"critical slowing down","score":0.8360000252723694},{"id":"https://openalex.org/keywords/learning-dynamics","display_name":"learning dynamics","score":0.7739999890327454},{"id":"https://openalex.org/keywords/aleatoric-uncertainty","display_name":"aleatoric uncertainty","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8346079587936401},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7966033816337585},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6131329536437988},{"id":"https://openalex.org/C79416737","wikidata":"https://www.wikidata.org/wiki/Q2305519","display_name":"Social learning","level":2,"score":0.589238166809082},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5552018284797668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.526367723941803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47589099407196045},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4690214693546295},{"id":"https://openalex.org/C171578705","wikidata":"https://www.wikidata.org/wiki/Q5418700","display_name":"Evolutionary dynamics","level":3,"score":0.4193708896636963},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3394537568092346},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23556405305862427},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14932119846343994},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.14648181200027466},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.13097083568572998},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.11194846034049988},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.08521440625190735},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3201333390","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2109.07259.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:3201333390","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2109.07259.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W52153049","https://openalex.org/W131709709","https://openalex.org/W309803593","https://openalex.org/W582220661","https://openalex.org/W644087790","https://openalex.org/W1192553058","https://openalex.org/W1526328753","https://openalex.org/W1541084404","https://openalex.org/W1596771711","https://openalex.org/W1685866933","https://openalex.org/W1766695457","https://openalex.org/W1876456565","https://openalex.org/W1908253641","https://openalex.org/W1963754118","https://openalex.org/W1986840174","https://openalex.org/W1995622844","https://openalex.org/W2026069625","https://openalex.org/W2036651296","https://openalex.org/W2036817197","https://openalex.org/W2039656410","https://openalex.org/W2040889951","https://openalex.org/W2050495532","https://openalex.org/W2051432898","https://openalex.org/W2057171149","https://openalex.org/W2063012336","https://openalex.org/W2067393629","https://openalex.org/W2081485018","https://openalex.org/W2085728653","https://openalex.org/W2088956500","https://openalex.org/W2089047045","https://openalex.org/W2096016260","https://openalex.org/W2100677568","https://openalex.org/W2106713015","https://openalex.org/W2117726420","https://openalex.org/W2118416350","https://openalex.org/W2119567691","https://openalex.org/W2128797809","https://openalex.org/W2133627192","https://openalex.org/W2133993682","https://openalex.org/W2149126181","https://openalex.org/W2158282517","https://openalex.org/W2160084302","https://openalex.org/W2167062553","https://openalex.org/W2168226964","https://openalex.org/W2214144476","https://openalex.org/W2226396244","https://openalex.org/W2399928304","https://openalex.org/W2413708867","https://openalex.org/W2545546008","https://openalex.org/W2549525793","https://openalex.org/W2742987999","https://openalex.org/W2747213132","https://openalex.org/W2754697090","https://openalex.org/W2788300737","https://openalex.org/W2808252900","https://openalex.org/W2810161095","https://openalex.org/W2811498230","https://openalex.org/W2883304604","https://openalex.org/W2890391327","https://openalex.org/W2907440173","https://openalex.org/W2911283634","https://openalex.org/W2942432719","https://openalex.org/W2944782467","https://openalex.org/W2955418163","https://openalex.org/W2981679938","https://openalex.org/W2991401196","https://openalex.org/W2994836491","https://openalex.org/W3006462484","https://openalex.org/W3012323720","https://openalex.org/W3028473954","https://openalex.org/W3029326706","https://openalex.org/W3034204965","https://openalex.org/W3037624623","https://openalex.org/W3103039747","https://openalex.org/W3107081604","https://openalex.org/W3164062244","https://openalex.org/W3177125472"],"related_works":["https://openalex.org/W4224100200","https://openalex.org/W2338754536","https://openalex.org/W7097174043","https://openalex.org/W2099050992","https://openalex.org/W2031571562","https://openalex.org/W4413766826","https://openalex.org/W4283772308","https://openalex.org/W2290302229","https://openalex.org/W7198108289","https://openalex.org/W2007303123"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,61,110],"derive":[4],"and":[5,37,54,97,133,142,158],"present":[6],"evolutionary":[7,165],"reinforcement":[8],"learning":[9,47,52,71,88,107,128,138,160],"dynamics":[10,28,139,147],"in":[11,75,154],"which":[12],"the":[13,19,23,27,51,76,105,127,134,137,164],"agents":[14],"are":[15,148],"irreducibly":[16],"uncertain":[17],"about":[18],"current":[20],"state":[21],"of":[22,32,78,114,126,136,167],"environment.":[24],"We":[25],"evaluate":[26],"across":[29],"different":[30],"classes":[31],"partially":[33],"observable":[34],"agent-environment":[35],"systems":[36],"find":[38,64,111],"that":[39,65],"irreducible":[40,90],"environmental":[41,91,168],"uncertainty":[42,92],"can":[43],"lead":[44],"to":[45,84,103,161],"better":[46],"outcomes":[48],"faster,":[49],"stabilize":[50],"process":[53],"overcome":[55],"social":[56,156],"dilemmas.":[57],"However,":[58],"as":[59],"expected,":[60],"do":[62],"also":[63],"partial":[66,119],"observability":[67],"may":[68],"cause":[69],"worse":[70],"outcomes,":[72],"for":[73,152],"example,":[74],"form":[77],"a":[79,112,122,149],"catastrophic":[80],"limit":[81],"cycle.":[82],"Compared":[83],"fully":[85],"observant":[86],"agents,":[87],"with":[89],"often":[93],"requires":[94],"more":[95],"exploration":[96],"less":[98],"weight":[99],"on":[100],"future":[101],"rewards":[102],"obtain":[104],"best":[106],"outcomes.":[108],"Furthermore,":[109],"range":[113],"dynamical":[115],"effects":[116,166],"induced":[117],"by":[118],"observability,":[120],"e.g.,":[121],"critical":[123],"slowing":[124],"down":[125],"processes":[129],"between":[130],"reward":[131],"regimes":[132],"separation":[135],"into":[140],"fast":[141],"slow":[143],"directions.":[144],"The":[145],"presented":[146],"practical":[150],"tool":[151],"researchers":[153],"biology,":[155],"science":[157],"machine":[159],"systematically":[162],"investigate":[163],"uncertainty.":[169]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2021-09-27T00:00:00"}