{"id":"https://openalex.org/W11162148","doi":null,"title":"Adaptive Agents with Reinforcement Learning and Internal Memory","display_name":"Adaptive Agents with Reinforcement Learning and Internal Memory","alternate_titles":[],"publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W11162148","mag":"11162148"},"language":"en","primary_location":{"id":"pmh:oai:re.public.polimi.it:11311/271596","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/271596","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"parent_works":[],"lineage":["https://openalex.org/W11162148"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5040796351","display_name":"Pier Luca Lanzi","orcid":"https://orcid.org/0000-0002-1933-7717","observed_orcids":["https://orcid.org/0000-0002-1933-7717"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Pier Luca Lanzi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1933-7717","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5040796351"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5507,"has_fulltext":false,"cited_by_count":53,"citation_normalized_percentile":{"value":0.92601651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"342"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0003000000142492354,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":9.999999747378752e-05,"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/perceptual-aliasing","display_name":"perceptual aliasing","score":0.9110000133514404},{"id":"https://openalex.org/keywords/internal-memory","display_name":"internal memory","score":0.8859999775886536},{"id":"https://openalex.org/keywords/adaptive-agents","display_name":"adaptive agents","score":0.984000027179718},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9909999966621399},{"id":"https://openalex.org/keywords/learning-classifier-systems","display_name":"learning classifier systems","score":0.925000011920929},{"id":"https://openalex.org/keywords/tabular-reinforcement-learning","display_name":"tabular reinforcement learning","score":0.9309999942779541}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.732101321220398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.642539381980896},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6077254414558411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36124131083488464},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12713655829429626},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08893728256225586}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:re.public.polimi.it:11311/271596","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/271596","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:11162148","doi":null,"is_oa":false,"landing_page_url":"https://ci.nii.ac.jp/naid/20000415634","pdf_url":null,"source":{"id":"https://openalex.org/S4306420888","display_name":"Simulation of Adaptive Behavior","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Simulation of Adaptive Behavior","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.38.6410","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.38.6410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.bham.ac.uk/pub/authors/T.Kovacs/lcs.archive/Lanzi2000c.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2411359688","https://openalex.org/W7117976779","https://openalex.org/W4237402488","https://openalex.org/W1657674574","https://openalex.org/W2159498728","https://openalex.org/W1508784758","https://openalex.org/W2224606000","https://openalex.org/W2052117683","https://openalex.org/W2061361125","https://openalex.org/W1702278112"],"abstract_inverted_index":{"Perceptual":[0],"aliasing":[1,38],"is":[2,11],"a":[3,12,51],"serious":[4],"problem":[5],"for":[6,35],"adaptive":[7,41],"agents.":[8],"Internal":[9],"memory":[10,34],"promising":[13],"approach":[14],"to":[15,20,49],"extend":[16],"reinforcement":[17,44,67],"learning":[18,68,70],"algorithms":[19],"problems":[21,39],"involving":[22],"perceptual":[23,37],"aliasing.":[24],"In":[25],"this":[26],"paper":[27],"we":[28,47],"investigate":[29],"the":[30],"effectiveness":[31],"of":[32,54],"internal":[33],"tackling":[36],"with":[40],"agents":[42],"and":[43,69],"learning.":[45],"Specifically,":[46],"try":[48],"give":[50],"unified":[52],"view":[53],"some":[55],"interesting":[56],"results":[57],"that":[58],"have":[59],"been":[60],"presented":[61],"in":[62],"different":[63],"frameworks,":[64],"i.e.:":[65],"tabular":[66],"classifier":[71],"systems.":[72]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W11162148","counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2016-06-24T00:00:00"}
