{"id":"https://openalex.org/W2139053308","doi":"https://doi.org/10.1109/robot.2004.1307456","title":"Policy gradient reinforcement learning for fast quadrupedal locomotion","display_name":"Policy gradient reinforcement learning for fast quadrupedal locomotion","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2139053308","doi":"https://doi.org/10.1109/robot.2004.1307456","mag":"2139053308"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2004.1307456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2004.1307456","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":"conference-paper","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/A5037610596","display_name":"Nate Kohl","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"N. Kohl","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","Dept. of Comput. Sci., Texas Univ., Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Texas Univ., Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Stone","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","Dept. of Comput. Sci., Texas Univ., Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Texas Univ., Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":43.2376,"has_fulltext":false,"cited_by_count":588,"citation_normalized_percentile":{"value":0.99966551,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2619","last_page":"2624 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":0.9991000294685364,"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":0.9991000294685364,"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":0.9930999875068665,"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/T11170","display_name":"Biomimetic flight and propulsion mechanisms","score":0.9731000065803528,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.8535950779914856},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7612902522087097},{"id":"https://openalex.org/keywords/quadrupedalism","display_name":"Quadrupedalism","score":0.7506373524665833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7300595045089722},{"id":"https://openalex.org/keywords/gait","display_name":"Gait","score":0.6438746452331543},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5524317026138306},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.5415563583374023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43003350496292114},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.35517075657844543}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8535950779914856},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7612902522087097},{"id":"https://openalex.org/C134181672","wikidata":"https://www.wikidata.org/wiki/Q21907045","display_name":"Quadrupedalism","level":2,"score":0.7506373524665833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7300595045089722},{"id":"https://openalex.org/C151800584","wikidata":"https://www.wikidata.org/wiki/Q2370000","display_name":"Gait","level":2,"score":0.6438746452331543},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5524317026138306},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.5415563583374023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43003350496292114},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.35517075657844543},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/robot.2004.1307456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2004.1307456","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:CiteSeerX.psu:10.1.1.5.685","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.5.685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/pstone/Papers/bib2html/../bib2html-links/icra04.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.73.9580","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.73.9580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/pstone/Papers/bib2html-links/icra04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.4244","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.4244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.utexas.edu/users/pstone/Papers/bib2html-links/icra04.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1483589","https://openalex.org/W12965381","https://openalex.org/W101458385","https://openalex.org/W1525400443","https://openalex.org/W1904894153","https://openalex.org/W2064817422","https://openalex.org/W2079497341","https://openalex.org/W2108734173","https://openalex.org/W2112002204","https://openalex.org/W2130105540","https://openalex.org/W2144446635","https://openalex.org/W2155027007","https://openalex.org/W2166772492","https://openalex.org/W2432517183","https://openalex.org/W2796837256","https://openalex.org/W3011120880","https://openalex.org/W3103182070","https://openalex.org/W4285719527","https://openalex.org/W6600051106","https://openalex.org/W6600517022","https://openalex.org/W6604131640","https://openalex.org/W6639801864","https://openalex.org/W6670434882","https://openalex.org/W6683204974","https://openalex.org/W6684656089","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W4388251424","https://openalex.org/W2008498579","https://openalex.org/W2923272690","https://openalex.org/W2559825912","https://openalex.org/W1966935220","https://openalex.org/W2064963663","https://openalex.org/W1992956164","https://openalex.org/W2775028049","https://openalex.org/W2087283056","https://openalex.org/W1536304773"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,9,17,22,28,59,95,109],"machine":[4],"learning":[5,34],"approach":[6,57],"to":[7,35,88],"optimizing":[8],"quadrupedal":[10,62],"trot":[11],"gait":[12,96,102],"for":[13,21,104],"forward":[14],"speed.":[15],"Given":[16],"parameterized":[18],"walk":[19],"designed":[20],"specific":[23],"robot,":[24],"we":[25],"propose":[26],"using":[27],"form":[29],"of":[30,40,46,74,111],"policy":[31],"gradient":[32],"reinforcement":[33],"automatically":[36],"search":[37],"the":[38,44,48,66,78,90,92,105],"set":[39],"possible":[41,50],"parameters":[42],"with":[43,82],"goal":[45],"finding":[47],"fastest":[49],"walk.":[51],"We":[52],"implement":[53],"and":[54,81,114],"test":[55],"our":[56],"on":[58,77],"commercially":[60],"available":[61],"robot":[63],"platform,":[64],"namely":[65],"Sony":[67],"Aibo":[68],"robot.":[69],"After":[70],"about":[71],"three":[72],"hours":[73],"learning,":[75],"all":[76],"physical":[79],"robots":[80,93],"no":[83],"human":[84],"intervention":[85],"other":[86],"than":[87,98],"change":[89],"batteries,":[91],"achieved":[94],"faster":[97],"any":[99],"previously":[100],"known":[101,103],"Aibo,":[106],"significantly":[107],"outperforming":[108],"variety":[110],"existing":[112],"hand-coded":[113],"learned":[115],"solutions.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":48},{"year":2020,"cited_by_count":35},{"year":2019,"cited_by_count":55},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":35},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":31},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":25},{"year":2012,"cited_by_count":21}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}