{"id":"https://openalex.org/W3020104292","doi":"https://doi.org/10.1145/3377930.3390214","title":"Evolving inborn knowledge for fast adaptation in dynamic POMDP problems","display_name":"Evolving inborn knowledge for fast adaptation in dynamic POMDP problems","publication_year":2020,"publication_date":"2020-06-25","ids":{"openalex":"https://openalex.org/W3020104292","doi":"https://doi.org/10.1145/3377930.3390214","mag":"3020104292"},"language":"en","primary_location":{"id":"doi:10.1145/3377930.3390214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377930.3390214","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","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2004.12846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016734804","display_name":"Eseoghene Ben-Iwhiwhu","orcid":null},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Eseoghene Ben-Iwhiwhu","raw_affiliation_strings":["Loughborough University, Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023634954","display_name":"Pawe\u0142 \u0141adosz","orcid":"https://orcid.org/0000-0002-1154-8333"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pawel Ladosz","raw_affiliation_strings":["Loughborough University, Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047569491","display_name":"Jeffery Dick","orcid":"https://orcid.org/0000-0003-2496-5299"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeffery Dick","raw_affiliation_strings":["Loughborough University, Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428822","display_name":"Wen\u2010Hua Chen","orcid":"https://orcid.org/0000-0003-3356-2889"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wen-Hua Chen","raw_affiliation_strings":["Loughborough University, Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055443197","display_name":"Praveen K. Pilly","orcid":"https://orcid.org/0000-0001-9762-2882"},"institutions":[{"id":"https://openalex.org/I200576644","display_name":"HRL Laboratories (United States)","ror":"https://ror.org/05p7te762","country_code":"US","type":"company","lineage":["https://openalex.org/I200576644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Praveen Pilly","raw_affiliation_strings":["HRL Laboratories"],"affiliations":[{"raw_affiliation_string":"HRL Laboratories","institution_ids":["https://openalex.org/I200576644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049155414","display_name":"Andrea Soltoggio","orcid":"https://orcid.org/0000-0002-9750-8358"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Soltoggio","raw_affiliation_strings":["Loughborough University, Loughborough, UK"],"affiliations":[{"raw_affiliation_string":"Loughborough University, Loughborough, UK","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016734804"],"corresponding_institution_ids":["https://openalex.org/I143804889"],"apc_list":null,"apc_paid":null,"fwci":0.8118,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78633996,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"280","last_page":"288"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8750379085540771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8266305923461914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6517711877822876},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6377665400505066},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6323293447494507},{"id":"https://openalex.org/keywords/neuroevolution","display_name":"Neuroevolution","score":0.5843541026115417},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5835825204849243},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5666579604148865},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5384860038757324},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38647782802581787},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.08736765384674072}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8750379085540771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8266305923461914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6517711877822876},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6377665400505066},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6323293447494507},{"id":"https://openalex.org/C118070581","wikidata":"https://www.wikidata.org/wiki/Q2060528","display_name":"Neuroevolution","level":3,"score":0.5843541026115417},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5835825204849243},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5666579604148865},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5384860038757324},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38647782802581787},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.08736765384674072},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3377930.3390214","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377930.3390214","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","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/b028ada0-6437-4f94-a198-26dacc43603f","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/b028ada0-6437-4f94-a198-26dacc43603f","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Ben-Iwhiwhu, E, Ladosz, P, Dick, J, Chen, W H, Pilly, P & Soltoggio, A 2020, Evolving inborn knowledge for fast adaptation in dynamic POMDP problems. in GECCO 2020 : Proceedings of the 2020 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, New York, NY, pp. 280-288. https://doi.org/10.1145/3377930.3390214","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:2004.12846","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12846","pdf_url":"https://arxiv.org/pdf/2004.12846","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"},{"id":"pmh:oai:figshare.com:article/12278087","is_oa":true,"landing_page_url":"https://figshare.com/articles/Evolving_inborn_knowledge_for_fast_adaptation_in_dynamic_POMDP_problems/12278087","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.12846","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.12846","pdf_url":"https://arxiv.org/pdf/2004.12846","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":44,"referenced_works":["https://openalex.org/W20283819","https://openalex.org/W124233690","https://openalex.org/W182104509","https://openalex.org/W189103237","https://openalex.org/W1498436455","https://openalex.org/W1542791059","https://openalex.org/W1598377843","https://openalex.org/W1780128256","https://openalex.org/W1996579288","https://openalex.org/W2111935653","https://openalex.org/W2124290836","https://openalex.org/W2137825550","https://openalex.org/W2143200432","https://openalex.org/W2145339207","https://openalex.org/W2151710526","https://openalex.org/W2161251531","https://openalex.org/W2173248099","https://openalex.org/W2342662072","https://openalex.org/W2480004914","https://openalex.org/W2541877577","https://openalex.org/W2550182557","https://openalex.org/W2578206533","https://openalex.org/W2596367596","https://openalex.org/W2604763608","https://openalex.org/W2605353576","https://openalex.org/W2767097881","https://openalex.org/W2778749116","https://openalex.org/W2787501667","https://openalex.org/W2890208753","https://openalex.org/W2906697496","https://openalex.org/W2914752403","https://openalex.org/W2923504512","https://openalex.org/W2952526277","https://openalex.org/W2953072278","https://openalex.org/W2954989419","https://openalex.org/W2963581679","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W2964282857","https://openalex.org/W2996898812","https://openalex.org/W3131821236","https://openalex.org/W4251311522","https://openalex.org/W4289388948","https://openalex.org/W4300971732"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W2168909409","https://openalex.org/W3013693939","https://openalex.org/W2964282857","https://openalex.org/W4299507693","https://openalex.org/W2735796404","https://openalex.org/W3123911006","https://openalex.org/W2811365478","https://openalex.org/W2735321217","https://openalex.org/W2962258836"],"abstract_inverted_index":{"Rapid":[0],"online":[1,61,91,171],"adaptation":[2,87,175],"to":[3,70,89,107,135,157,181,191],"changing":[4],"tasks":[5],"is":[6,40],"an":[7,75,117],"important":[8],"problem":[9],"in":[10,26,36,119,139,179,193],"machine":[11],"learning":[12,22,56,62,72,92,185],"and,":[13],"recently,":[14],"a":[15,37,109,120,140],"focus":[16],"of":[17,32,60,103,116,124,131,142,148,167],"meta-reinforcement":[18,184],"learning.":[19],"However,":[20],"reinforcement":[21],"(RL)":[23],"algorithms":[24],"struggle":[25],"POMDP":[27],"environments":[28],"because":[29],"the":[30,33,65,68,99,113,125,129,132,146,155,194],"state":[31],"system,":[34],"essential":[35],"RL":[38],"framework,":[39],"not":[41,49],"always":[42],"visible.":[43],"Additionally,":[44],"hand-designed":[45],"meta-RL":[46],"architectures":[47],"may":[48],"include":[50],"suitable":[51],"computational":[52],"structures":[53],"for":[54],"specific":[55,90],"problems.":[57,93],"The":[58,122,165,187],"evolution":[59],"mechanisms,":[63],"on":[64],"contrary,":[66],"has":[67],"ability":[69,130,156],"incorporate":[71],"strategies":[73],"into":[74],"agent":[76],"that":[77,111,150,161],"can":[78],"(i)":[79],"evolve":[80,108,158],"memory":[81],"when":[82],"required":[83],"and":[84,154,170,176],"(ii)":[85],"optimize":[86],"speed":[88],"In":[94],"this":[95],"paper,":[96],"we":[97],"exploit":[98],"highly":[100],"adaptive":[101],"nature":[102],"neuromodulated":[104],"neural":[105],"networks":[106,127],"controller":[110],"uses":[112],"latent":[114],"space":[115],"autoencoder":[118],"POMDP.":[121],"analysis":[123],"evolved":[126],"reveals":[128],"proposed":[133],"algorithm":[134,188],"acquire":[136],"inborn":[137,168],"knowledge":[138,169],"variety":[141],"aspects":[143],"such":[144],"as":[145],"detection":[147],"cues":[149],"reveal":[151],"implicit":[152],"rewards,":[153],"location":[159],"neurons":[160],"help":[162],"with":[163],"navigation.":[164],"integration":[166],"plasticity":[172],"enabled":[173],"fast":[174],"better":[177],"performance":[178],"comparison":[180],"some":[182],"non-evolutionary":[183],"algorithms.":[186],"proved":[189],"also":[190],"succeed":[192],"3D":[195],"gaming":[196],"environment":[197],"Malmo":[198],"Minecraft.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2020-11-23T00:00:00"}