{"id":"https://openalex.org/W2066461256","doi":"https://doi.org/10.1109/robio.2011.6181710","title":"Reinforcement learning of ball-in-a-cup playing robot","display_name":"Reinforcement learning of ball-in-a-cup playing robot","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2066461256","doi":"https://doi.org/10.1109/robio.2011.6181710","mag":"2066461256"},"language":"en","primary_location":{"id":"doi:10.1109/robio.2011.6181710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2011.6181710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Robotics and Biomimetics","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/A5020114289","display_name":"Bojan Nemec","orcid":"https://orcid.org/0000-0002-8728-7731"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Bojan Nemec","raw_affiliation_strings":["Department of Automatics, Biocybernetics, and Robotics, Jo\u017eef Stefan Institute, Ljubljana, Slovenia","Jo\u017eef Stefan Institute, Department of Automatics, Biocybernetics, and Robotics, 1000 Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automatics, Biocybernetics, and Robotics, Jo\u017eef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]},{"raw_affiliation_string":"Jo\u017eef Stefan Institute, Department of Automatics, Biocybernetics, and Robotics, 1000 Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019399129","display_name":"Ale\u0161 Ude","orcid":"https://orcid.org/0000-0003-3677-3972"},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Ales Ude","raw_affiliation_strings":["Department of Automatics, Biocybernetics, and Robotics, Jo\u017eef Stefan Institute, Ljubljana, Slovenia","Jo\u017eef Stefan Institute, Department of Automatics, Biocybernetics, and Robotics, 1000 Ljubljana, Slovenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automatics, Biocybernetics, and Robotics, Jo\u017eef Stefan Institute, Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]},{"raw_affiliation_string":"Jo\u017eef Stefan Institute, Department of Automatics, Biocybernetics, and Robotics, 1000 Ljubljana, Slovenia","institution_ids":["https://openalex.org/I3006985408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3006985408"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"165","issue":null,"first_page":"2682","last_page":"2987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976999759674072,"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":0.9889000058174133,"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":0.9004768133163452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7261897921562195},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6874755024909973},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6604927778244019},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.6483463048934937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6377521753311157},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5031268000602722},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4898078143596649},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.4120936393737793},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34803056716918945},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.27661651372909546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13776472210884094}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9004768133163452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7261897921562195},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6874755024909973},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6604927778244019},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6483463048934937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6377521753311157},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5031268000602722},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4898078143596649},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.4120936393737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34803056716918945},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.27661651372909546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13776472210884094},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio.2011.6181710","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio.2011.6181710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Robotics and Biomimetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1516801383","https://openalex.org/W1746819321","https://openalex.org/W1910378657","https://openalex.org/W1967097499","https://openalex.org/W1975318316","https://openalex.org/W2012392077","https://openalex.org/W2041812416","https://openalex.org/W2110304639","https://openalex.org/W2116226448","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2124758444","https://openalex.org/W2125612430","https://openalex.org/W2130801532","https://openalex.org/W2148467756","https://openalex.org/W2161872510","https://openalex.org/W2166302491","https://openalex.org/W2312442049","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4250912612","https://openalex.org/W6653435097","https://openalex.org/W6676348739","https://openalex.org/W6679257226"],"related_works":["https://openalex.org/W1976483367","https://openalex.org/W1812381063","https://openalex.org/W2097725510","https://openalex.org/W2171128163","https://openalex.org/W2373034895","https://openalex.org/W155730701","https://openalex.org/W2360485332","https://openalex.org/W1924069939","https://openalex.org/W2352079541","https://openalex.org/W2542410050"],"abstract_inverted_index":{"An":[0],"autonomous":[1],"robot,":[2],"which":[3,120],"makes":[4],"decisions":[5],"based":[6],"on":[7,93,122],"previous":[8,75,114],"experience":[9,76],"and":[10,77],"feedback":[11],"from":[12,83,127],"its":[13],"sensors":[14],"is":[15,34,50,62,131],"one":[16],"of":[17,70,95],"the":[18,23,59,65,71,87,144],"challenges":[19],"in":[20,40],"robotics.":[21],"Among":[22],"most":[24],"promising":[25],"framework":[26],"to":[27,46,56,63,78,80,124,142],"bring":[28],"traditional":[29,105],"robotics":[30],"towards":[31],"true":[32],"autonomy":[33],"reinforcement":[35,38,60],"learning.":[36],"However,":[37],"learning":[39,61,94,108,119],"high":[41],"dimensional":[42],"spaces":[43],"usually":[44],"required":[45],"encode":[47],"robot":[48],"tasks":[49],"extremely":[51],"difficult.":[52],"The":[53],"key":[54],"idea":[55,92],"speed":[57],"up":[58],"limit":[64],"potentially":[66],"huge":[67],"search":[68],"space":[69],"policy":[72],"by":[73,107],"using":[74,104,112],"generalize":[79],"new":[81,125],"policies":[82,126],"similar":[84,128],"cases.":[85,129],"In":[86],"paper":[88],"we":[89,100,117],"evaluate":[90],"this":[91,102,134],"ball-in-a-cup":[96],"playing":[97],"robot.":[98],"First":[99],"solve":[101],"problem":[103],"approach":[106,136],"action-value":[109],"function":[110],"without":[111],"any":[113],"knowledge.":[115],"Next,":[116],"propose":[118],"relies":[121],"generalizing":[123],"It":[130],"shown,":[132],"that":[133],"latter":[135],"dramatically":[137],"reduces":[138],"number":[139],"cycles":[140],"needed":[141],"learn":[143],"appropriate":[145],"policy.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}