{"id":"https://openalex.org/W2076552100","doi":"https://doi.org/10.1177/105971239700500307","title":"Measuring the Effectiveness of Reinforcement Learning for Behavior-Based Robots","display_name":"Measuring the Effectiveness of Reinforcement Learning for Behavior-Based Robots","publication_year":1997,"publication_date":"1997-01-01","ids":{"openalex":"https://openalex.org/W2076552100","doi":"https://doi.org/10.1177/105971239700500307","mag":"2076552100"},"language":"en","primary_location":{"id":"doi:10.1177/105971239700500307","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239700500307","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/A5070018517","display_name":"John Shackleton","orcid":null},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Shackleton","raw_affiliation_strings":["University of Minnesota 200 Union Street SE, Room 4-192, Minoeapolis"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota 200 Union Street SE, Room 4-192, Minoeapolis","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016462041","display_name":"Maria Gini","orcid":"https://orcid.org/0000-0001-8841-1055"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maria Gini","raw_affiliation_strings":["University of Minnesota 200 Union Street SE, Room 4-192, Minoeapolis","Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota 200 Union Street SE, Room 4-192, Minoeapolis","institution_ids":["https://openalex.org/I130238516"]},{"raw_affiliation_string":"Computer Science and Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070018517"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.15113076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"5","issue":"3-4","first_page":"365","last_page":"390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9976000189781189,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8351473808288574},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.7414695024490356},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7139188051223755},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6739004254341125},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5859658122062683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5749160051345825},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5392189621925354},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5076345205307007},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3822616934776306},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3506661057472229},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.106408029794693},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0814509391784668},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06456232070922852}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8351473808288574},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.7414695024490356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139188051223755},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6739004254341125},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5859658122062683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5749160051345825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5392189621925354},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5076345205307007},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3822616934776306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3506661057472229},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.106408029794693},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0814509391784668},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06456232070922852},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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:10.1177/105971239700500307","is_oa":false,"landing_page_url":"https://doi.org/10.1177/105971239700500307","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:10.1.1.35.4123","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.35.4123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umn.edu/~gini/papers/adaptive.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W18781575","https://openalex.org/W32403112","https://openalex.org/W969698184","https://openalex.org/W1605318140","https://openalex.org/W1607817625","https://openalex.org/W1979071892","https://openalex.org/W2012036715","https://openalex.org/W2065356613","https://openalex.org/W2097856935","https://openalex.org/W2101915445","https://openalex.org/W2107166378","https://openalex.org/W2107726111","https://openalex.org/W2134814908","https://openalex.org/W2161694911","https://openalex.org/W2198041288","https://openalex.org/W2583413467","https://openalex.org/W2886362482","https://openalex.org/W4254384028"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2086122291","https://openalex.org/W1987513656","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"We":[0,57],"explore":[1],"the":[2,8,15,23,30,38,67,78,82],"use":[3],"of":[4,10,17,40,63,66,77,95],"behavior-based":[5,20],"architectures":[6,21],"within":[7],"context":[9],"reinforcement":[11],"learning":[12,41,68],"and":[13,28,54,75,86],"examine":[14,58],"effects":[16],"using":[18],"different":[19],"on":[22,81,91],"ability":[24,83],"to":[25,42,70,72,84],"learn":[26],"correctly":[27],"efficiently":[29],"task":[31,39],"at":[32],"hand.":[33],"In":[34],"particular,":[35],"we":[36,87],"study":[37],"push":[43],"boxes":[44],"in":[45],"a":[46,92],"simulated":[47],"two-dimensional":[48],"environment":[49],"originally":[50],"proposed":[51],"by":[52],"Mahadevan":[53],"Connell":[55],"(1992).":[56],"issues":[59],"such":[60],"as":[61],"effectiveness":[62],"learning,":[64],"flexibility":[65],"method":[69],"adapt":[71],"new":[73],"environments,":[74],"effect":[76],"behavior":[79],"architecture":[80],"learn,":[85],"report":[88],"results":[89],"obtained":[90],"large":[93],"number":[94],"simulation":[96],"runs.":[97]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}