{"id":"https://openalex.org/W2119717200","doi":"https://doi.org/10.1007/bf00992696","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","display_name":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","publication_year":1992,"publication_date":"1992-05-01","ids":{"openalex":"https://openalex.org/W2119717200","doi":"https://doi.org/10.1007/bf00992696","mag":"2119717200"},"language":"en","primary_location":{"id":"doi:10.1007/bf00992696","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992696","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992696.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/BF00992696.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112059424","display_name":"Ronald J. Williams","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ronald J. Williams","raw_affiliation_strings":["College of Computer Science, 161 CN, Northeastern University, 360 Huntington Ave., 02115, Boston, MA","College of Computer Science, 161 CN, Northeastern University, 360 Huntington Ave., Boston, MA 02115. rjw@corwin.ccs.northeastern.edu#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, 161 CN, Northeastern University, 360 Huntington Ave., 02115, Boston, MA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"College of Computer Science, 161 CN, Northeastern University, 360 Huntington Ave., Boston, MA 02115. rjw@corwin.ccs.northeastern.edu#TAB#","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112059424"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":14.5083,"has_fulltext":true,"cited_by_count":7451,"citation_normalized_percentile":{"value":0.98925994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"8","issue":"3-4","first_page":"229","last_page":"256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9927999973297119,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9927999973297119,"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/T11513","display_name":"stochastic dynamics and bifurcation","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9581999778747559,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8258216977119446},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7855746746063232},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6905362606048584},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5880454182624817},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5560203194618225},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.5513932704925537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5234272480010986},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4982273578643799},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4574865400791168},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.45713695883750916},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4242442846298218},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.41037869453430176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3863964080810547},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19862887263298035}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8258216977119446},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7855746746063232},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905362606048584},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5880454182624817},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5560203194618225},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.5513932704925537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234272480010986},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4982273578643799},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4574865400791168},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.45713695883750916},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4242442846298218},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41037869453430176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3863964080810547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19862887263298035},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/bf00992696","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992696","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992696.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.8871","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.8871","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ualberta.ca/~sutton/williams-92.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.8399","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.8399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ftp.ccs.neu.edu/pub/people/rjw/conn-reinf-ml-92.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.31.2545","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.2545","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.ccs.neu.edu/pub/people/rjw/conn-reinf-ml-92.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/bf00992696","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992696","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992696.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G811241986","display_name":"Connectionist Learning Algorithms for Temporal Processing   and Multi-Scale Search","funder_award_id":"8921275","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2119717200.pdf","grobid_xml":"https://content.openalex.org/works/W2119717200.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W105751747","https://openalex.org/W354832773","https://openalex.org/W569156507","https://openalex.org/W1505136099","https://openalex.org/W1538558539","https://openalex.org/W1547224907","https://openalex.org/W1569296262","https://openalex.org/W1569320505","https://openalex.org/W1573503290","https://openalex.org/W1610678877","https://openalex.org/W1652505363","https://openalex.org/W1968743014","https://openalex.org/W1993411524","https://openalex.org/W2009796613","https://openalex.org/W2021801581","https://openalex.org/W2043968544","https://openalex.org/W2068896964","https://openalex.org/W2080759927","https://openalex.org/W2091565802","https://openalex.org/W2100677568","https://openalex.org/W2101130101","https://openalex.org/W2102673654","https://openalex.org/W2152475379","https://openalex.org/W2160575156","https://openalex.org/W2166082022","https://openalex.org/W2565808444","https://openalex.org/W2766736793","https://openalex.org/W2796556654","https://openalex.org/W2949173247","https://openalex.org/W3011120880","https://openalex.org/W3121926921","https://openalex.org/W3207342693","https://openalex.org/W4300402905","https://openalex.org/W6632269551","https://openalex.org/W6632924624","https://openalex.org/W6634074277","https://openalex.org/W6636530465","https://openalex.org/W6682302528","https://openalex.org/W6780394890","https://openalex.org/W6820729035","https://openalex.org/W7024637854"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2021128377","https://openalex.org/W2604685715","https://openalex.org/W350032239","https://openalex.org/W2412160900","https://openalex.org/W134701156"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":40},{"year":2025,"cited_by_count":394},{"year":2024,"cited_by_count":543},{"year":2023,"cited_by_count":698},{"year":2022,"cited_by_count":660},{"year":2021,"cited_by_count":1129},{"year":2020,"cited_by_count":1070},{"year":2019,"cited_by_count":921},{"year":2018,"cited_by_count":682},{"year":2017,"cited_by_count":338},{"year":2016,"cited_by_count":145},{"year":2015,"cited_by_count":70},{"year":2014,"cited_by_count":51},{"year":2013,"cited_by_count":62},{"year":2012,"cited_by_count":80}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}
