{"id":"https://openalex.org/W154839746","doi":null,"title":"Towards a supervised dyna-Q application on a robotic manipulator","display_name":"Towards a supervised dyna-Q application on a robotic manipulator","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W154839746","mag":"154839746"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.5748","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.5748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aass.oru.se/Research/Learning/publications/2005/Skoglund_etal_2005-SAIS-SSLS-Towards_a_Supervised_Dyna-Q_Application.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5057799639","display_name":"Alexander Skoglund","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Skoglund","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024471324","display_name":"Rainer Palm","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rainer Palm","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088202291","display_name":"Tom Duckett","orcid":"https://orcid.org/0000-0003-2971-7905","observed_orcids":["https://orcid.org/0000-0003-2971-7905"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Duckett","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2971-7905","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3341,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65015101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/dyna-q","display_name":"Dyna-Q","score":0.7480000257492065},{"id":"https://openalex.org/keywords/robot-manipulators","display_name":"robot manipulators","score":0.5529999732971191},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.5989999771118164},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5559999942779541},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.9900000095367432},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"curse of dimensionality","score":0.7369999885559082},{"id":"https://openalex.org/keywords/high-dimensional-state-spaces","display_name":"high-dimensional state spaces","score":0.7099999785423279},{"id":"https://openalex.org/keywords/data-capture","display_name":"data capture","score":0.42500001192092896},{"id":"https://openalex.org/keywords/articulated-manipulator","display_name":"articulated manipulator","score":0.30399999022483826}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6861618161201477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6824893951416016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6365398168563843},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6071773767471313},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5868673920631409},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5612305402755737},{"id":"https://openalex.org/C190727649","wikidata":"https://www.wikidata.org/wiki/Q1941532","display_name":"Mobile manipulator","level":4,"score":0.5574632287025452},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5537515878677368},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5192685127258301},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4691682457923889},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.4388793706893921},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.42199257016181946},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4148150384426117},{"id":"https://openalex.org/C2781347998","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Manipulator (device)","level":3,"score":0.4112522006034851},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3391987085342407},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1592749059200287},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0962415337562561},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08060824871063232},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.5748","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.5748","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aass.oru.se/Research/Learning/publications/2005/Skoglund_etal_2005-SAIS-SSLS-Towards_a_Supervised_Dyna-Q_Application.pdf","raw_type":"text"},{"id":"mag:154839746","doi":null,"is_oa":false,"landing_page_url":"http://www.diva-portal.org/smash/record.jsf?pid=diva2:138392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W315691377","https://openalex.org/W577932262","https://openalex.org/W1481615754","https://openalex.org/W1980035368","https://openalex.org/W1988882685","https://openalex.org/W2009574384","https://openalex.org/W2046372172","https://openalex.org/W2048226872","https://openalex.org/W2121863487","https://openalex.org/W2124776405","https://openalex.org/W2131246644","https://openalex.org/W2135376858","https://openalex.org/W2341171179"],"related_works":["https://openalex.org/W3128307014","https://openalex.org/W6884980669","https://openalex.org/W387911743","https://openalex.org/W3215163890","https://openalex.org/W1232610009","https://openalex.org/W3153356475","https://openalex.org/W2965739887","https://openalex.org/W7100679092","https://openalex.org/W7203607191","https://openalex.org/W2981233685"],"abstract_inverted_index":{"Abstract":[0],"\u2014":[1],"Having":[2],"a":[3,8,28,47,50,166],"robot":[4,60],"that":[5,73,152,164],"can":[6],"learn":[7],"task":[9,167],"shown":[10,57],"to":[11,25,42,58,84,108,119,140,155,160],"it":[12,175],"is":[13,56,61,68,118],"an":[14,85,162],"challenge":[15],"for":[16,21],"robotic":[17,83],"scientists":[18],"and":[19,65,131,146],"useful":[20],"nonengineers":[22],"who":[23],"want":[24],"interact":[26],"with":[27,88,104],"robot.":[29],"In":[30],"this":[31,135],"paper":[32],"we":[33,76,138],"address":[34],"some":[35],"of":[36,54,71,123,144],"the":[37,59,69,121,127],"difficulties":[38],"one":[39,62,66,153],"will":[40],"have":[41],"overcome":[43],"when":[44,75,158],"developing":[45],"such":[46,63],"system.":[48],"Making":[49],"good":[51],"data":[52],"capturing":[53],"what":[55],"problem,":[64],"other":[67],"curse":[70,122],"dimensionality":[72,124],"arises":[74],"apply":[77],"techniques":[78],"successfully":[79],"applied":[80],"in":[81,134,168],"mobile":[82,94],"articulated":[86],"manipulator":[87],"more":[89,179],"degrees-of-freedom":[90],"(d.o.f.)":[91],"than":[92],"most":[93],"robots":[95],"on":[96],"wheels.":[97],"We":[98,148],"use":[99],"reinforcement":[100],"learning":[101,106],"(RL)":[102],"together":[103],"supervised":[105],"(SL)":[107],"gain":[109],"benefits":[110],"from":[111,126],"both":[112],"paradigms.":[113],"A":[114],"key":[115],"scientific":[116],"challange":[117],"adress":[120,141],"arising":[125],"high":[128],"dimensional":[129],"state":[130],"action":[132],"space":[133],"application,":[136],"which":[137],"propose":[139],"by":[142],"combination":[143],"RL":[145],"SL.":[147],"also":[149],"point":[150],"out":[151],"has":[154],"be":[156],"careful":[157],"trying":[159],"obtain":[161],"agent":[163],"learns":[165],"as":[169,172],"few":[170],"trials":[171],"possible,":[173],"since":[174],"might":[176],"require":[177],"much":[178],"computational":[180],"time.":[181],"I.":[182]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}
