{"id":"https://openalex.org/W3046241732","doi":"https://doi.org/10.1145/3377929.3389946","title":"Safer reinforcement learning through evolved instincts","display_name":"Safer reinforcement learning through evolved instincts","publication_year":2020,"publication_date":"2020-07-08","ids":{"openalex":"https://openalex.org/W3046241732","doi":"https://doi.org/10.1145/3377929.3389946","mag":"3046241732"},"language":"en","primary_location":{"id":"doi:10.1145/3377929.3389946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377929.3389946","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":["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/A5089907783","display_name":"Djordje Grbic","orcid":"https://orcid.org/0000-0002-4388-2539"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Djordje Grbic","raw_affiliation_strings":["IT University Copenhagen"],"affiliations":[{"raw_affiliation_string":"IT University Copenhagen","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020511097","display_name":"Sebastian Risi","orcid":"https://orcid.org/0000-0003-3607-8400"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Sebastian Risi","raw_affiliation_strings":["IT University Copenhagen"],"affiliations":[{"raw_affiliation_string":"IT University Copenhagen","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089907783"],"corresponding_institution_ids":["https://openalex.org/I83467386"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53694354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"77","last_page":"78"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9936000108718872,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8709072470664978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7408642768859863},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.6940548419952393},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.572464644908905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5695900917053223},{"id":"https://openalex.org/keywords/hazard","display_name":"Hazard","score":0.5215073227882385},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.4987342357635498},{"id":"https://openalex.org/keywords/instinct","display_name":"Instinct","score":0.4895645081996918},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.47604990005493164},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38205385208129883},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3731200098991394},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3080448806285858},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15483805537223816}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8709072470664978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408642768859863},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.6940548419952393},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.572464644908905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5695900917053223},{"id":"https://openalex.org/C49261128","wikidata":"https://www.wikidata.org/wiki/Q1132455","display_name":"Hazard","level":2,"score":0.5215073227882385},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.4987342357635498},{"id":"https://openalex.org/C3232509","wikidata":"https://www.wikidata.org/wiki/Q18237","display_name":"Instinct","level":2,"score":0.4895645081996918},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.47604990005493164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38205385208129883},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3731200098991394},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3080448806285858},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15483805537223816},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3377929.3389946","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377929.3389946","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:pure.atira.dk:publications/704b619d-f68e-4cf8-824d-39507d649551","is_oa":false,"landing_page_url":"https://pure.itu.dk/portal/da/publications/704b619d-f68e-4cf8-824d-39507d649551","pdf_url":null,"source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Grbic, D & Risi, S 2020, Safer reinforcement learning through evolved instincts. in GECCO '20 : Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion. Association for Computing Machinery, pp. 77-78. https://doi.org/10.1145/3377929.3389946","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4206497039"],"related_works":["https://openalex.org/W2357264280","https://openalex.org/W2349142772","https://openalex.org/W2953205341","https://openalex.org/W2400156683","https://openalex.org/W235065745","https://openalex.org/W2029935773","https://openalex.org/W2787754950","https://openalex.org/W4294873804","https://openalex.org/W4383109125","https://openalex.org/W2891227010"],"abstract_inverted_index":{"An":[0],"important":[1],"goal":[2],"in":[3,49,60,67,160,180],"reinforcement":[4,51,122],"learning":[5,105,123],"is":[6,37,54,116,209],"to":[7,14,28,44,82,102,165,167,186,188,190],"create":[8],"agents":[9,35,81,101,185],"that":[10,24,76,99,202],"can":[11,138],"quickly":[12],"adapt":[13],"new":[15,46,169,191],"goals":[16],"but":[17,137],"at":[18],"the":[19,61,73,77,111,114,134,140,144,162],"same":[20],"time":[21],"avoid":[22],"situations":[23],"might":[25],"cause":[26],"damage":[27],"themselves":[29],"or":[30],"their":[31],"environments.":[32],"One":[33],"way":[34],"learn":[36,166,187],"through":[38,121],"exploration":[39,53],"mechanisms,":[40],"which":[41,129,161],"are":[42],"needed":[43],"discover":[45],"policies.":[47],"However,":[48],"deep":[50],"learning,":[52],"normally":[55],"done":[56],"by":[57],"injecting":[58],"noise":[59],"action":[62],"space.":[63],"While":[64,173],"performing":[65],"well":[66],"many":[68],"domains,":[69],"this":[70,87],"setup":[71],"has":[72,164],"inherent":[74],"risk":[75],"noisy":[78,141],"actions":[79],"lead":[80],"unsafe":[83],"environment":[84],"states.":[85,109],"In":[86],"paper,":[88],"we":[89],"introduce":[90],"a":[91,117,152,174,210],"novel":[92],"approach":[93,115,168,212],"called":[94],"Meta-Learned":[95],"Instinctual":[96],"Networks":[97],"(MLIN)":[98],"allows":[100,184],"perform":[103],"lifetime":[104,136],"while":[106,193],"avoiding":[107],"hazardous":[108],"At":[110],"core":[112],"of":[113,143],"plastic":[118,145],"network":[119,177,208],"trained":[120],"and":[124],"an":[125,206],"evolved":[126],"\"instinctual\"":[127],"network,":[128],"does":[130],"not":[131],"change":[132],"during":[133,171],"agent's":[135],"modulate":[139],"output":[142],"network.":[146],"We":[147],"test":[148],"our":[149],"idea":[150],"on":[151],"simple":[153],"2D":[154],"navigation":[155],"task":[156],"with":[157,196,205],"hazard":[158,197],"zones,":[159],"agent":[163],"targets":[170,192],"deployment.":[172],"standard":[175],"meta-trained":[176],"performs":[178],"poorly":[179],"these":[181],"tasks,":[182],"MLIN":[183],"navigate":[189],"minimizing":[194],"collisions":[195],"zones.":[198],"These":[199],"results":[200],"suggest":[201],"meta-learning":[203],"augmented":[204],"instinctual":[207],"promising":[211],"for":[213],"safe":[214],"AI.":[215]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}