{"id":"https://openalex.org/W3046326017","doi":"https://doi.org/10.1145/3377929.3389901","title":"Adaptive reinforcement learning through evolving self-modifying neural networks","display_name":"Adaptive reinforcement learning through evolving self-modifying neural networks","publication_year":2020,"publication_date":"2020-07-08","ids":{"openalex":"https://openalex.org/W3046326017","doi":"https://doi.org/10.1145/3377929.3389901","mag":"3046326017"},"language":"en","primary_location":{"id":"doi:10.1145/3377929.3389901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377929.3389901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.05832","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Samuel Schmidgall","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Samuel Schmidgall","raw_affiliation_strings":["George Mason University"],"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162714631"],"apc_list":null,"apc_paid":null,"fwci":0.5488,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73563009,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9954000115394592,"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":0.7706999778747559},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6299999952316284},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.39419999718666077},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.35530000925064087},{"id":"https://openalex.org/keywords/adaptive-behavior","display_name":"Adaptive behavior","score":0.34700000286102295},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.34360000491142273},{"id":"https://openalex.org/keywords/adaptive-system","display_name":"Adaptive system","score":0.33739998936653137}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7706999778747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694599986076355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6134999990463257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.39419999718666077},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C68784500","wikidata":"https://www.wikidata.org/wiki/Q1570691","display_name":"Adaptive behavior","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C2910496060","wikidata":"https://www.wikidata.org/wiki/Q4680720","display_name":"Adaptive behaviour","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3377929.3389901","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377929.3389901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.05832","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.05832","pdf_url":"https://arxiv.org/pdf/2006.05832","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.05832","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.05832","pdf_url":"https://arxiv.org/pdf/2006.05832","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"adaptive":[1],"learning":[2,136],"capabilities":[3],"seen":[4],"in":[5,22,27,90],"biological":[6],"neural":[7,56],"networks":[8,57,127],"are":[9,128],"largely":[10],"a":[11,39,91,102],"product":[12],"of":[13,46,88,98,104,131],"the":[14,44,86,99,108,116,140],"self-modifying":[15,125],"behavior":[16],"emerging":[17],"from":[18],"online":[19,47],"plastic":[20,126],"changes":[21],"synaptic":[23],"connectivity.":[24],"Current":[25],"methods":[26],"Reinforcement":[28],"Learning":[29],"(RL)":[30],"only":[31],"adjust":[32],"to":[33,64,77,80,110,133,151],"new":[34],"interactions":[35],"after":[36],"reflection":[37],"over":[38],"specified":[40],"time":[41,150],"interval,":[42],"preventing":[43],"emergence":[45],"adaptivity.":[48],"Recent":[49],"work":[50],"addressing":[51],"this":[52],"by":[53,112],"endowing":[54],"artificial":[55],"with":[58,115],"neuromodulated":[59],"plasticity":[60],"have":[61,75],"been":[62],"shown":[63],"improve":[65],"performance":[66],"on":[67],"simple":[68],"RL":[69],"tasks":[70],"trained":[71],"using":[72,124,144],"backpropagation,":[73],"but":[74],"yet":[76],"scale":[78],"up":[79],"larger":[81],"problems.":[82],"Here":[83],"we":[84],"study":[85],"problem":[87],"meta-learning":[89,135],"challenging":[92],"quadruped":[93,100],"domain,":[94],"where":[95],"each":[96],"leg":[97],"has":[101],"chance":[103],"becoming":[105],"unusable,":[106],"requiring":[107],"agent":[109],"adapt":[111],"continuing":[113],"locomotion":[114],"remaining":[117],"limbs.":[118],"Results":[119],"demonstrate":[120],"that":[121],"agents":[122],"evolved":[123],"more":[129],"capable":[130],"adapting":[132],"complex":[134],"tasks,":[137],"even":[138],"outperforming":[139],"same":[141],"network":[142],"updated":[143],"gradient-based":[145],"algorithms":[146],"while":[147],"taking":[148],"less":[149],"train.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2020-08-07T00:00:00"}