{"id":"https://openalex.org/W2029372064","doi":"https://doi.org/10.1109/icra.2012.6225154","title":"Implementation of an embodied general reinforcement learner on a serial link manipulator","display_name":"Implementation of an embodied general reinforcement learner on a serial link manipulator","publication_year":2012,"publication_date":"2012-05-01","ids":{"openalex":"https://openalex.org/W2029372064","doi":"https://doi.org/10.1109/icra.2012.6225154","mag":"2029372064"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2012.6225154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2012.6225154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-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/A5113982277","display_name":"Nicholas Malone","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nicholas Malone","raw_affiliation_strings":["University of New Mexico;"],"affiliations":[{"raw_affiliation_string":"University of New Mexico;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068167226","display_name":"Brandon Rohrer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brandon Rohrer","raw_affiliation_strings":["Sandia National Lab"],"affiliations":[{"raw_affiliation_string":"Sandia National Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060753774","display_name":"Lydia Tapia","orcid":"https://orcid.org/0000-0002-7822-7091"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lydia Tapia","raw_affiliation_strings":["University of New Mexico;"],"affiliations":[{"raw_affiliation_string":"University of New Mexico;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111847818","display_name":"R. Lumia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ron Lumia","raw_affiliation_strings":["University of New Mexico;"],"affiliations":[{"raw_affiliation_string":"University of New Mexico;","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030412645","display_name":"John Wood","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Wood","raw_affiliation_strings":["University of New Mexico;"],"affiliations":[{"raw_affiliation_string":"University of New Mexico;","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5113982277"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.09156299,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"5","issue":null,"first_page":"862","last_page":"869"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9919000267982483,"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":0.9236750602722168},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7698158025741577},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6825030446052551},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5549703240394592},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4873676896095276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45301252603530884},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43489086627960205},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3342031240463257},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0866994559764862}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9236750602722168},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698158025741577},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6825030446052551},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5549703240394592},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4873676896095276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45301252603530884},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43489086627960205},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3342031240463257},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0866994559764862},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2012.6225154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2012.6225154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.49000000953674316,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310632","display_name":"Center for Evolutionary and Theoretical Immunology","ror":"https://ror.org/05fs6jp91"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1548797027","https://openalex.org/W1589064538","https://openalex.org/W1885639605","https://openalex.org/W1986014385","https://openalex.org/W2002196558","https://openalex.org/W2029514605","https://openalex.org/W2108886361","https://openalex.org/W2115951219","https://openalex.org/W2128990851","https://openalex.org/W2162470099","https://openalex.org/W2290874868","https://openalex.org/W2312998612","https://openalex.org/W2333638880","https://openalex.org/W2398031410","https://openalex.org/W2404812813","https://openalex.org/W2524898811","https://openalex.org/W4214717370","https://openalex.org/W4235899661","https://openalex.org/W6632959618","https://openalex.org/W6676020571","https://openalex.org/W6727610073","https://openalex.org/W6844919503","https://openalex.org/W6998947608"],"related_works":["https://openalex.org/W2380179524","https://openalex.org/W4283365723","https://openalex.org/W2963001125","https://openalex.org/W2091233881","https://openalex.org/W2352366064","https://openalex.org/W4250820896","https://openalex.org/W2124102101","https://openalex.org/W4250305970","https://openalex.org/W1484550171","https://openalex.org/W1570928019"],"abstract_inverted_index":{"BECCA":[0,51,154],"(a":[1],"Brain-Emulating":[2],"Cognition":[3],"and":[4,41,108,127,165],"Control":[5],"Architecture":[6],"software":[7],"package)":[8],"was":[9],"developed":[10],"in":[11,26,116,170],"order":[12],"to":[13,20,29,70,76,78,91,99,118,138,147,166],"perform":[14,30,100],"general":[15],"reinforcement":[16,42,73,131,155],"learning,":[17],"that":[18],"is,":[19],"enable":[21],"unmodeled":[22],"embodied":[23],"systems":[24],"operating":[25,173],"unstructured":[27],"environments":[28],"unfamiliar":[31],"tasks.":[32],"It":[33],"accomplishes":[34],"this":[35,171],"through":[36],"automatic":[37],"paired":[38],"feature":[39],"creation":[40],"learning":[43,90,98,115,122,156],"algorithms.":[44],"This":[45],"paper":[46,145,172],"describes":[47],"an":[48],"implementation":[49],"of":[50,56,67,143,152,161],"on":[52,105,174],"a":[53,65],"seven":[54],"Degree":[55],"Freedom":[57],"(DoF)":[58],"Barrett":[59],"Whole":[60],"Arm":[61],"Manipulator":[62],"(WAM)":[63],"undergoing":[64],"series":[66],"experiments":[68],"designed":[69],"test":[71],"the":[72,79,83,85,93,130,144,150,153,162,168],"learner's":[74],"ability":[75],"adapt":[77],"WAM":[80,94],"hardware.":[81,177],"In":[82],"experiments,":[84],"following":[86],"is":[87,146],"demonstrated,":[88],"1)":[89],"transition":[92],"between":[95],"states,":[96],"2)":[97],"at":[101],"near":[102],"optimal":[103],"levels":[104],"one,":[106],"two":[107],"three":[109],"dimensional":[110],"navigation":[111],"tasks,":[112],"3)":[113],"applying":[114],"simulation":[117],"hardware":[119],"performance,":[120],"4)":[121],"under":[123],"inconsistent,":[124],"human-generated":[125],"reward,":[126],"5)":[128],"combining":[129],"learner":[132],"with":[133],"Probabilistic":[134],"Roadmap":[135],"Methods":[136],"(PRM)":[137],"improve":[139],"scalability.":[140],"The":[141],"goal":[142],"demonstrate":[148],"both":[149],"scalability":[151],"approach":[157,169],"using":[158],"different":[159],"formulations":[160],"state":[163],"space":[164],"show":[167],"complex":[175],"physical":[176]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}