{"id":"https://openalex.org/W2144280078","doi":"https://doi.org/10.1109/robot.2002.1014235","title":"A study of reinforcement learning for the robot with many degrees of freedom - acquisition of locomotion patterns for multi-legged robot","display_name":"A study of reinforcement learning for the robot with many degrees of freedom - acquisition of locomotion patterns for multi-legged robot","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2144280078","doi":"https://doi.org/10.1109/robot.2002.1014235","mag":"2144280078"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2002.1014235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2002.1014235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292)","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/A5102255303","display_name":"K. Ito","orcid":"https://orcid.org/0009-0003-7353-1654"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Ito","raw_affiliation_strings":["Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015434555","display_name":"Fumitoshi Matsuno","orcid":"https://orcid.org/0000-0001-9685-3267"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"F. Matsuno","raw_affiliation_strings":["Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"3392","last_page":"3397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10879","display_name":"Robotic Locomotion and Control","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9980000257492065,"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":0.9921000003814697,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.807365894317627},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7302013635635376},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6574376821517944},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6181766390800476},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6108772158622742},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5493788123130798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5434267520904541},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.5392054915428162},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5111001133918762},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4502592980861664},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4352872371673584},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.41726404428482056},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3943890929222107},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16687893867492676},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14381012320518494}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.807365894317627},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7302013635635376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6574376821517944},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6181766390800476},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6108772158622742},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5493788123130798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5434267520904541},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.5392054915428162},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5111001133918762},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4502592980861664},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4352872371673584},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.41726404428482056},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3943890929222107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16687893867492676},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14381012320518494},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robot.2002.1014235","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2002.1014235","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1557517019","https://openalex.org/W2261323909","https://openalex.org/W2341205486","https://openalex.org/W3028232160","https://openalex.org/W4214717370","https://openalex.org/W6692336637","https://openalex.org/W6704228173"],"related_works":["https://openalex.org/W1976483367","https://openalex.org/W1812381063","https://openalex.org/W2171128163","https://openalex.org/W4361733995","https://openalex.org/W2373034895","https://openalex.org/W155730701","https://openalex.org/W2544716473","https://openalex.org/W2360485332","https://openalex.org/W2126211886","https://openalex.org/W2352079541"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,10,51,63,82],"has":[2,32],"recently":[3],"been":[4],"receiving":[5],"much":[6],"attention":[7],"as":[8,22],"a":[9,70,79,111,132],"method":[11],"for":[12,109,131],"not":[13,27],"only":[14],"toy":[15],"problems":[16],"but":[17],"also":[18],"complicated":[19],"systems":[20,100],"such":[21],"robot":[23,112,134],"systems.":[24],"It":[25],"does":[26],"need":[28],"priori":[29],"knowledge":[30],"and":[31,37,105],"higher":[33],"capability":[34],"of":[35,42,55,61,88,117,123,128],"reactive":[36],"adaptive":[38],"behaviors.":[39],"However,":[40],"increasing":[41],"action-state":[43,72],"space":[44,90],"makes":[45],"it":[46],"difficult":[47],"to":[48,66,99],"accomplish":[49],"the":[50,56,59,62,121,124,139],"process.":[52],"In":[53],"most":[54],"previous":[57],"works,":[58],"application":[60],"is":[64,97],"restricted":[65],"simple":[67],"tasks":[68],"with":[69,85,101,113],"small":[71],"space.":[73],"Considering":[74],"this":[75],"point,":[76],"we":[77],"present":[78],"new":[80],"reinforcement":[81],"algorithm:":[83],"Q-learning":[84],"dynamic":[86],"structuring":[87],"exploration":[89],"based":[91],"on":[92],"genetic":[93],"algorithm.":[94,150],"The":[95],"algorithm":[96,126],"applicable":[98],"high":[102],"dimensional":[103],"action":[104],"interior":[106],"state":[107],"spaces,":[108],"example,":[110],"many":[114],"redundant":[115],"degrees":[116],"freedom.":[118],"To":[119],"demonstrate":[120],"effectiveness":[122],"proposed":[125,149],"simulations":[127],"locomotion":[129],"patterns":[130],"12-leged":[133],"were":[135],"carried":[136],"out.":[137],"As":[138],"result,":[140],"an":[141],"effective":[142],"behavior":[143],"was":[144],"obtained":[145],"by":[146],"using":[147],"our":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}