{"id":"https://openalex.org/W2795951333","doi":"https://doi.org/10.1109/devlrn.2017.8329800","title":"The effects on adaptive behaviour of negatively valenced signals in reinforcement learning","display_name":"The effects on adaptive behaviour of negatively valenced signals in reinforcement learning","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2795951333","doi":"https://doi.org/10.1109/devlrn.2017.8329800","mag":"2795951333"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2017.8329800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","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/A5040711005","display_name":"Nicol\u00e1s Navarro-Guerrero","orcid":"https://orcid.org/0000-0003-1164-5579"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nicolas Navarro-Guerrero","raw_affiliation_strings":["Department of Informatics, Universitat Hamburg, Hamburg, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Universitat Hamburg, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101951215","display_name":"Robert Lowe","orcid":"https://orcid.org/0000-0002-0307-3171"},"institutions":[{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Robert J. Lowe","raw_affiliation_strings":["Department of Applied IT, University of Gothenburg, Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Applied IT, University of Gothenburg, Gothenburg, Sweden","institution_ids":["https://openalex.org/I881427289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["Universitat Hamburg, Hamburg, Hamburg, DE"],"affiliations":[{"raw_affiliation_string":"Universitat Hamburg, Hamburg, Hamburg, DE","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040711005"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":0.4253,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.62844825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"3","issue":null,"first_page":"148","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10056","display_name":"Neurotransmitter Receptor Influence on Behavior","score":0.9902999997138977,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8725231885910034},{"id":"https://openalex.org/keywords/punishment","display_name":"Punishment (psychology)","score":0.7639776468276978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6532053351402283},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6350124478340149},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6269252896308899},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5696719288825989},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.547614336013794},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5462103486061096},{"id":"https://openalex.org/keywords/animal-learning","display_name":"Animal learning","score":0.532132625579834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.530421793460846},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.47494032979011536},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4438548982143402},{"id":"https://openalex.org/keywords/carry","display_name":"Carry (investment)","score":0.4202580153942108},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.41539159417152405},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.22530174255371094},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15909844636917114},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07826507091522217}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8725231885910034},{"id":"https://openalex.org/C2779295839","wikidata":"https://www.wikidata.org/wiki/Q3544090","display_name":"Punishment (psychology)","level":2,"score":0.7639776468276978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532053351402283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6350124478340149},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6269252896308899},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5696719288825989},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.547614336013794},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5462103486061096},{"id":"https://openalex.org/C2992566924","wikidata":"https://www.wikidata.org/wiki/Q499210","display_name":"Animal learning","level":2,"score":0.532132625579834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.530421793460846},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.47494032979011536},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4438548982143402},{"id":"https://openalex.org/C2776299755","wikidata":"https://www.wikidata.org/wiki/Q432449","display_name":"Carry (investment)","level":2,"score":0.4202580153942108},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.41539159417152405},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.22530174255371094},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15909844636917114},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07826507091522217},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2017.8329800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2017.8329800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W76331760","https://openalex.org/W988357262","https://openalex.org/W1594303435","https://openalex.org/W1965692465","https://openalex.org/W1987777830","https://openalex.org/W2007028190","https://openalex.org/W2015051472","https://openalex.org/W2053011178","https://openalex.org/W2056419865","https://openalex.org/W2088222816","https://openalex.org/W2094842273","https://openalex.org/W2101539915","https://openalex.org/W2104440316","https://openalex.org/W2106411961","https://openalex.org/W2121294372","https://openalex.org/W2131241448","https://openalex.org/W2132473069","https://openalex.org/W2142213531","https://openalex.org/W2308085711","https://openalex.org/W2398806256","https://openalex.org/W2480707807","https://openalex.org/W2602871544","https://openalex.org/W2889572572","https://openalex.org/W2914484425","https://openalex.org/W2945153440","https://openalex.org/W4206062185","https://openalex.org/W4238404964","https://openalex.org/W4250012081","https://openalex.org/W6603190504","https://openalex.org/W6676179485","https://openalex.org/W6678911119","https://openalex.org/W6698535809"],"related_works":["https://openalex.org/W4361733995","https://openalex.org/W4310801741","https://openalex.org/W3140225428","https://openalex.org/W3042291365","https://openalex.org/W3196155444","https://openalex.org/W4321844043","https://openalex.org/W1988404251","https://openalex.org/W3088331655","https://openalex.org/W2130711276","https://openalex.org/W3210156800"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,9,48,77,92,137],"algorithms":[2],"and":[3,13,49,75,99,109],"particularly":[4],"those":[5],"based":[6,34],"on":[7,35,61,125],"temporal-difference":[8],"are":[10,33],"widely":[11],"adopted":[12],"have":[14,80],"been":[15],"successfully":[16],"applied":[17],"to":[18,27,96],"a":[19,68,145],"number":[20,146],"of":[21,56,59,73,113,133,147,150],"problems":[22],"as":[23,25],"well":[24],"used":[26],"model":[28],"animal":[29,76],"learning.":[30,62,126],"However,":[31],"they":[32],"neural":[36],"pathways":[37],"involved":[38],"in":[39],"reward-seeking":[40],"behaviour":[41],"since":[42],"little":[43],"is":[44],"known":[45],"about":[46,52],"punishment-driven":[47],"less":[50],"still":[51],"the":[53,111,130],"combined":[54],"effects":[55,89,112],"both":[57],"types":[58],"reinforcement":[60],"This":[63],"may":[64,85],"not":[65],"only":[66],"be":[67],"shortcoming":[69],"for":[70,90,123],"computational":[71],"models":[72],"human":[74],"but":[78],"we":[79,103],"recently":[81],"shown":[82],"that":[83],"it":[84],"also":[86],"carry":[87],"detrimental":[88],"machine":[91],"applications,":[93],"with":[94,120],"respect":[95],"task":[97],"performance":[98],"convergence":[100],"speed.":[101,138],"Here,":[102],"further":[104],"explore":[105],"our":[106],"original":[107,131],"results":[108],"compare":[110],"different":[114,121,148],"functions,":[115],"i.e.":[116],"binary,":[117],"linear,":[118],"exponential":[119],"variance,":[122],"punishment":[124,134,151],"Our":[127],"experiments":[128],"confirm":[129],"finding":[132],"signals":[135],"reducing":[136],"It":[139],"appears":[140],"this":[141],"result":[142],"generalizes":[143],"across":[144],"functions":[149],"reinforcement.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}