{"id":"https://openalex.org/W1965367179","doi":"https://doi.org/10.1177/105971239400200302","title":"Training Agents to Perform Sequential Behavior","display_name":"Training Agents to Perform Sequential Behavior","publication_year":1994,"publication_date":"1994-01-01","ids":{"openalex":"https://openalex.org/W1965367179","doi":"https://doi.org/10.1177/105971239400200302","mag":"1965367179"},"language":"en","primary_location":{"id":"doi:10.1177/105971239400200302","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239400200302","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-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/A5015551594","display_name":"Marco Colombetti","orcid":"https://orcid.org/0000-0003-2339-9678"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Colombetti","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024091899","display_name":"Marco Dorigo","orcid":"https://orcid.org/0000-0002-3971-0507"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marco Dorigo","raw_affiliation_strings":["Universit\u00e9 Libre de Bruxelles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Libre de Bruxelles","institution_ids":["https://openalex.org/I132053463"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.5367,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.98025499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2","issue":"3","first_page":"247","last_page":"275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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":0.9958000183105469,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9800000190734863,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9794999957084656,"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/trainer","display_name":"Trainer","score":0.7830063104629517},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7414650917053223},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6917095184326172},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5689367651939392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5338332056999207},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4320334494113922},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4200904965400696},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39353683590888977},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11999431252479553}],"concepts":[{"id":"https://openalex.org/C2780463512","wikidata":"https://www.wikidata.org/wiki/Q15122700","display_name":"Trainer","level":2,"score":0.7830063104629517},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7414650917053223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917095184326172},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5689367651939392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5338332056999207},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4320334494113922},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4200904965400696},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39353683590888977},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11999431252479553},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1177/105971239400200302","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239400200302","pdf_url":null,"source":{"id":"https://openalex.org/S183337005","display_name":"Adaptive Behavior","issn_l":"1059-7123","issn":["1059-7123","1741-2633"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptive Behavior","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.9757","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.9757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/ftp/global/pub/techreports/1993/tr-93-023.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.648.2135","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.648.2135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://http.icsi.berkeley.edu/ftp/global/pub/techreports/1993/tr-93-023.pdf","raw_type":"text"},{"id":"pmh:oai:dipot.ulb.ac.be:2013/74577","is_oa":false,"landing_page_url":"https://dipot.ulb.ac.be/dspace/bitstream/2013/74577/4/87e1ae9b-124b-436b-aaa5-efa21f9fec0c.txt","pdf_url":null,"source":{"id":"https://openalex.org/S4306401063","display_name":"D\u00e9p\u00f4t institutionnel de l'Universit\u00e9 libre de Bruxelles (Universit\u00e9 Libre de Bruxelles)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I132053463","host_organization_name":"Universit\u00e9 Libre de Bruxelles","host_organization_lineage":["https://openalex.org/I132053463"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Adaptive behavior, 2 (3","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:re.public.polimi.it:11311/518113","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/518113","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,"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/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W20846018","https://openalex.org/W32403112","https://openalex.org/W53052996","https://openalex.org/W143529956","https://openalex.org/W183068496","https://openalex.org/W192142699","https://openalex.org/W1481882669","https://openalex.org/W1497256448","https://openalex.org/W1509263472","https://openalex.org/W1511493290","https://openalex.org/W1532944971","https://openalex.org/W1557517019","https://openalex.org/W1600536735","https://openalex.org/W1976379984","https://openalex.org/W1979071892","https://openalex.org/W1995417003","https://openalex.org/W2012036715","https://openalex.org/W2018642704","https://openalex.org/W2065356613","https://openalex.org/W2068721938","https://openalex.org/W2106157970","https://openalex.org/W2108889070","https://openalex.org/W2134814908","https://openalex.org/W2152150600","https://openalex.org/W2913091258","https://openalex.org/W3011120880","https://openalex.org/W3023540311","https://openalex.org/W3028232160","https://openalex.org/W3037058914","https://openalex.org/W4206665516"],"related_works":["https://openalex.org/W1866966336","https://openalex.org/W4388176369","https://openalex.org/W1985489398","https://openalex.org/W638029546","https://openalex.org/W4285792946","https://openalex.org/W2920061524","https://openalex.org/W2000494260","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W154293939"],"abstract_inverted_index":{"This":[0],"article":[1],"is":[2,32,59,89,101,159,190],"concerned":[3],"with":[4,181],"training":[5,164],"an":[6,197],"agent":[7,106],"to":[8,22,161,184,200,209,224],"perform":[9],"sequential":[10],"behavior.":[11],"In":[12,42],"previous":[13],"work,":[14],"we":[15,48,112,154,233],"have":[16],"been":[17,222],"applying":[18],"reinforcement":[19,120,132],"learning":[20,97,125,208],"techniques":[21],"control":[23],"a":[24,28,90,134,137,213,225,244],"reactive":[25,30],"agent.":[26],"Obviously,":[27],"purely":[29],"system":[31],"limited":[33],"in":[34,55,73,168,212,243],"the":[35,62,81,105,108,117,124,130,143,170,173,179,187,201,230],"kind":[36],"of":[37,53,64,83,92,98,119,145,172,203,241],"interactions":[38],"it":[39,44,88],"can":[40,45],"learn.":[41],"particular,":[43],"learn":[46,70],"what":[47,220],"call":[49],"pseudosequences\u2014that":[50],"is,":[51,166],"sequences":[52,100],"actions":[54,75],"which":[56,74,122,158,169,206],"each":[57],"action":[58],"selected":[60,78],"on":[61,80],"basis":[63,82],"current":[65],"sensory":[66],"stimuli.":[67],"It":[68],"cannot":[69],"proper":[71,99],"sequences,":[72],"must":[76],"be":[77],"also":[79,140,195],"some":[84],"internal":[85],"state.":[86],"Moreover,":[87],"result":[91],"our":[93],"research":[94],"that":[95],"effective":[96],"improved":[102],"by":[103,239],"letting":[104],"and":[107,217,237],"trainer":[109,180],"communicate.":[110],"First,":[111],"consider":[113],"trainer-to-agent":[114],"communication,":[115,157],"introducing":[116],"concept":[118],"sensor,":[121],"lets":[123],"robot":[126],"explicitly":[127],"know":[128],"whether":[129,186],"last":[131],"was":[133],"reward":[135],"or":[136,192],"punishment.":[138],"We":[139,194],"show":[141,196],"how":[142],"use":[144],"this":[146],"sensor":[147],"makes":[148],"error":[149],"recovery":[150],"rules":[151],"emerge.":[152],"Then":[153],"introduce":[155],"agent-to-trainer":[156],"used":[160],"disambiguate":[162],"ambiguous":[163,204],"situations\u2014that":[165],"situations":[167],"observation":[171],"agent's":[174,188],"behavior":[175,211],"does":[176],"not":[177],"provide":[178],"enough":[182],"information":[183],"decide":[185],"move":[189],"right":[191],"wrong.":[193],"alternative":[198],"solution":[199],"problem":[202],"situations,":[205],"involves":[207],"coordinate":[210],"simpler,":[214],"unambiguous":[215],"setting":[216],"then":[218],"transferring":[219],"has":[221],"learned":[223],"more":[226],"complex":[227],"situation.":[228],"All":[229],"design":[231],"choices":[232],"make":[234],"are":[235],"discussed":[236],"compared":[238],"means":[240],"experiments":[242],"simulated":[245],"world.":[246]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}