{"id":"https://openalex.org/W3200610166","doi":"https://doi.org/10.1080/0952813x.2022.2153272","title":"Reinforcement with iterative punishment","display_name":"Reinforcement with iterative punishment","publication_year":2022,"publication_date":"2022-12-13","ids":{"openalex":"https://openalex.org/W3200610166","doi":"https://doi.org/10.1080/0952813x.2022.2153272","mag":"3200610166"},"language":"en","primary_location":{"id":"doi:10.1080/0952813x.2022.2153272","is_oa":false,"landing_page_url":"https://doi.org/10.1080/0952813x.2022.2153272","pdf_url":null,"source":{"id":"https://openalex.org/S153467142","display_name":"Journal of Experimental & Theoretical Artificial Intelligence","issn_l":"0952-813X","issn":["0952-813X","1362-3079"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Experimental & Theoretical Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://philsci-archive.pitt.edu/19546/1/iterative_reinforcement_with_punishment.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040179661","display_name":"Jeffrey A. Barrett","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeffrey A. Barrett","raw_affiliation_strings":["Department of Logic and Philosophy of Science, UC Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Logic and Philosophy of Science, UC Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001631148","display_name":"Nathan Gabriel","orcid":"https://orcid.org/0000-0002-4501-3310"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathan Gabriel","raw_affiliation_strings":["Department of Logic and Philosophy of Science, UC Irvine, Irvine, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Logic and Philosophy of Science, UC Irvine, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040179661"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":32.737,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.99688848,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"36","issue":"7","first_page":"1361","last_page":"1383"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"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":0.9405999779701233,"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":0.8961389064788818},{"id":"https://openalex.org/keywords/punishment","display_name":"Punishment (psychology)","score":0.7383463978767395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7301149368286133},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6744500994682312},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6187226176261902},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5999077558517456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4748164415359497},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.4661969244480133},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.3324486017227173},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1559188961982727},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1219618022441864},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.0866500735282898}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8961389064788818},{"id":"https://openalex.org/C2779295839","wikidata":"https://www.wikidata.org/wiki/Q3544090","display_name":"Punishment (psychology)","level":2,"score":0.7383463978767395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301149368286133},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6744500994682312},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6187226176261902},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5999077558517456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4748164415359497},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.4661969244480133},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3324486017227173},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1559188961982727},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1219618022441864},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0866500735282898},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/0952813x.2022.2153272","is_oa":false,"landing_page_url":"https://doi.org/10.1080/0952813x.2022.2153272","pdf_url":null,"source":{"id":"https://openalex.org/S153467142","display_name":"Journal of Experimental & Theoretical Artificial Intelligence","issn_l":"0952-813X","issn":["0952-813X","1362-3079"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Experimental & Theoretical Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:philsci-archive.pitt.edu:19546","is_oa":true,"landing_page_url":null,"pdf_url":"http://philsci-archive.pitt.edu/19546/1/iterative_reinforcement_with_punishment.pdf","source":{"id":"https://openalex.org/S4306401282","display_name":"PhilSci-Archive (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"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":"NonPeerReviewed"}],"best_oa_location":{"id":"pmh:oai:philsci-archive.pitt.edu:19546","is_oa":true,"landing_page_url":null,"pdf_url":"http://philsci-archive.pitt.edu/19546/1/iterative_reinforcement_with_punishment.pdf","source":{"id":"https://openalex.org/S4306401282","display_name":"PhilSci-Archive (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"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":"NonPeerReviewed"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3200610166.pdf","grobid_xml":"https://content.openalex.org/works/W3200610166.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W10695593","https://openalex.org/W275510463","https://openalex.org/W1484520425","https://openalex.org/W1564229172","https://openalex.org/W2038134790","https://openalex.org/W2053392081","https://openalex.org/W2084987844","https://openalex.org/W2094581276","https://openalex.org/W2099262935","https://openalex.org/W2108758037","https://openalex.org/W2139420917","https://openalex.org/W2149820942","https://openalex.org/W2163569945","https://openalex.org/W2605830538","https://openalex.org/W3118687981","https://openalex.org/W4253759836","https://openalex.org/W4255012397"],"related_works":["https://openalex.org/W2761624296","https://openalex.org/W4386994694","https://openalex.org/W4388738109","https://openalex.org/W2362901947","https://openalex.org/W2362086884","https://openalex.org/W2920061524","https://openalex.org/W1606071314","https://openalex.org/W2350210972","https://openalex.org/W2019751999","https://openalex.org/W2006191342"],"abstract_inverted_index":{"We":[0,23,62],"consider":[1],"the":[2,17,26,67],"efficacy":[3],"of":[4,7,19,29,59,66,69],"various":[5],"forms":[6],"reinforcement":[8,30,60,70],"learning":[9,27,81],"with":[10,31,71],"punishment":[11,33,73],"in":[12,16,41,82],"evolving":[13,38],"linguistic":[14],"conventions":[15,40],"context":[18],"Lewis-Skyrms":[20],"signalling":[21,44],"games.":[22,45],"show":[24],"that":[25],"strategy":[28],"iterative":[32,72],"is":[34,47],"highly":[35],"effective":[36],"at":[37],"optimal":[39],"even":[42],"complex":[43],"It":[46],"also":[48],"robust":[49],"and":[50,74],"can":[51],"be":[52,78],"easily":[53],"extended":[54],"to":[55,80],"a":[56],"self-tuning":[57],"variety":[58],"learning.":[61],"briefly":[63],"discuss":[64],"some":[65],"virtues":[68],"how":[75],"it":[76],"may":[77],"related":[79],"nature.":[83]},"counts_by_year":[{"year":2025,"cited_by_count":17},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}