{"id":"https://openalex.org/W2098523767","doi":"https://doi.org/10.1109/robot.2004.1307522","title":"A simple reinforcement learning algorithm for biped walking","display_name":"A simple reinforcement learning algorithm for biped walking","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2098523767","doi":"https://doi.org/10.1109/robot.2004.1307522","mag":"2098523767"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2004.1307522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2004.1307522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://mediatum.ub.tum.de/node?id=1545418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025458882","display_name":"Jun Morimoto","orcid":"https://orcid.org/0000-0002-4115-1919"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"J. Morimoto","raw_affiliation_strings":["Department of Humanoid Robotics and Computational Neuroscience, ATR Computational Neuroscience Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Humanoid Robotics and Computational Neuroscience, ATR Computational Neuroscience Laboratories, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048975019","display_name":"Gordon Cheng","orcid":"https://orcid.org/0000-0003-0770-8717"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"G. Cheng","raw_affiliation_strings":["Department of Humanoid Robotics and Computational Neuroscience, ATR Computational Neuroscience Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Humanoid Robotics and Computational Neuroscience, ATR Computational Neuroscience Laboratories, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055330939","display_name":"Christopher G. Atkeson","orcid":"https://orcid.org/0000-0003-4265-8452"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.G. Atkeson","raw_affiliation_strings":["The Robotics Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"The Robotics Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068614605","display_name":"Garth Zeglin","orcid":"https://orcid.org/0000-0002-6680-4787"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Zeglin","raw_affiliation_strings":["The Robotics Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"The Robotics Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025458882"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":4.8644,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.95183505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3030","last_page":"3035 Vol.3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9901999831199646,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9692999720573425,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8342350721359253},{"id":"https://openalex.org/keywords/swing","display_name":"Swing","score":0.761198878288269},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7112969756126404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.709856390953064},{"id":"https://openalex.org/keywords/biped-robot","display_name":"Biped robot","score":0.6604491472244263},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5320124626159668},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4706898033618927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.438669890165329},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4238263964653015},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3882147967815399},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.36379343271255493},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16520333290100098}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8342350721359253},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"score":0.761198878288269},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7112969756126404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709856390953064},{"id":"https://openalex.org/C3019356360","wikidata":"https://www.wikidata.org/wiki/Q372949","display_name":"Biped robot","level":3,"score":0.6604491472244263},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5320124626159668},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4706898033618927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438669890165329},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4238263964653015},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3882147967815399},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.36379343271255493},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16520333290100098},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robot.2004.1307522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2004.1307522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1545418","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1545418","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1545418","is_oa":true,"landing_page_url":"http://mediatum.ub.tum.de/node?id=1545418","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W110801934","https://openalex.org/W135960858","https://openalex.org/W658381347","https://openalex.org/W1538222263","https://openalex.org/W1545656448","https://openalex.org/W1885639605","https://openalex.org/W1994923984","https://openalex.org/W2016102421","https://openalex.org/W2017970073","https://openalex.org/W2025752438","https://openalex.org/W2039091159","https://openalex.org/W2049374002","https://openalex.org/W2082872327","https://openalex.org/W2096498654","https://openalex.org/W2109910161","https://openalex.org/W2111527309","https://openalex.org/W2111999018","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2142992961","https://openalex.org/W2150714400","https://openalex.org/W2153917213","https://openalex.org/W2155307968","https://openalex.org/W2167804690","https://openalex.org/W2331734107","https://openalex.org/W4214717370","https://openalex.org/W4240768792","https://openalex.org/W4252510982","https://openalex.org/W4255358587","https://openalex.org/W4295133295","https://openalex.org/W6604488684","https://openalex.org/W7033823516"],"related_works":["https://openalex.org/W2360051520","https://openalex.org/W2798244654","https://openalex.org/W34871393","https://openalex.org/W3168108534","https://openalex.org/W1486689224","https://openalex.org/W2094697992","https://openalex.org/W4229574949","https://openalex.org/W2368813785","https://openalex.org/W2998806118","https://openalex.org/W842509023"],"abstract_inverted_index":{"We":[0,62,74],"propose":[1],"a":[2,26,42,48,54,60],"model-based":[3],"reinforcement":[4],"learning":[5],"algorithm":[6],"for":[7],"biped":[8,87],"walking":[9,36,67],"in":[10],"which":[11],"the":[12,18,30,34,45,65],"robot":[13],"learns":[14],"to":[15,53],"appropriately":[16],"place":[17],"swing":[19],"leg.":[20],"This":[21],"decision":[22],"is":[23],"based":[24,70],"on":[25,71,84],"learned":[27],"model":[28,39],"of":[29,33,47,59],"Poincare":[31],"map":[32],"periodic":[35],"pattern.":[37],"The":[38],"maps":[40],"from":[41],"state":[43,55],"at":[44,56],"middle":[46,58],"step":[49],"and":[50,78],"foot":[51],"placement":[52],"next":[57],"step.":[61],"also":[63],"modify":[64],"desired":[66],"cycle":[68],"frequency":[69],"online":[72],"measurements.":[73],"present":[75],"simulation":[76],"results,":[77],"are":[79],"currently":[80],"implementing":[81],"this":[82],"approach":[83],"an":[85],"actual":[86],"robot.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}