{"id":"https://openalex.org/W2028411224","doi":"https://doi.org/10.1109/ijcnn.2012.6252758","title":"Challenges for the policy representation when applying reinforcement learning in robotics","display_name":"Challenges for the policy representation when applying reinforcement learning in robotics","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2028411224","doi":"https://doi.org/10.1109/ijcnn.2012.6252758","mag":"2028411224"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2012.6252758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2012.6252758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2012 International Joint Conference on Neural Networks (IJCNN)","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/A5036281885","display_name":"Petar Kormushev","orcid":"https://orcid.org/0000-0002-6677-3044"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Petar Kormushev","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048780399","display_name":"Sylvain Calinon","orcid":"https://orcid.org/0000-0002-9036-6799"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sylvain Calinon","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044243940","display_name":"Darwin G. Caldwell","orcid":"https://orcid.org/0000-0002-6233-9961"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Darwin G. Caldwell","raw_affiliation_strings":["Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Department of Advanced Robotics, Istituto Italiano di Tecnologia, via Morego, 30,16163 Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080517829","display_name":"Barkan U\u011furlu","orcid":"https://orcid.org/0000-0002-9124-7441"},"institutions":[{"id":"https://openalex.org/I4840577","display_name":"Toyota Technological Institute","ror":"https://ror.org/001hv0k59","country_code":"JP","type":"education","lineage":["https://openalex.org/I4840577"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Barkan Ugurlu","raw_affiliation_strings":["Toyota Technological Institute, Nagoya, Japan","Toyota Technological Institute, 468-8511 Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute, Nagoya, Japan","institution_ids":["https://openalex.org/I4840577"]},{"raw_affiliation_string":"Toyota Technological Institute, 468-8511 Nagoya, Japan","institution_ids":["https://openalex.org/I4840577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036281885"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":2.8409,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90899837,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"165","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9976999759674072,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9912999868392944,"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/T10982","display_name":"Motor Control and Adaptation","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8278182148933411},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6798293590545654},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6779924631118774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5942286849021912},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5706669092178345},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3786325454711914},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3266545534133911},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.06855440139770508}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8278182148933411},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6798293590545654},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6779924631118774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5942286849021912},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5706669092178345},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3786325454711914},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3266545534133911},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.06855440139770508},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2012.6252758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2012.6252758","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2012 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.348.3208","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.348.3208","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.calinon.ch/papers/Kormushev-IJCNN2012.pdf","raw_type":"text"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/26060","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/26060","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 2012 International Joint Conference on Neural Networks (IJCNN)","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W200863839","https://openalex.org/W787204617","https://openalex.org/W1516801383","https://openalex.org/W1684361744","https://openalex.org/W1925816294","https://openalex.org/W1966268398","https://openalex.org/W1980440818","https://openalex.org/W1986014385","https://openalex.org/W2012392077","https://openalex.org/W2016765487","https://openalex.org/W2018547649","https://openalex.org/W2031580264","https://openalex.org/W2102162941","https://openalex.org/W2112361218","https://openalex.org/W2113698995","https://openalex.org/W2119717200","https://openalex.org/W2120772693","https://openalex.org/W2122777916","https://openalex.org/W2125079768","https://openalex.org/W2127107099","https://openalex.org/W2127572219","https://openalex.org/W2129515556","https://openalex.org/W2144741745","https://openalex.org/W2147828974","https://openalex.org/W2153817731","https://openalex.org/W2154543878","https://openalex.org/W2156671238","https://openalex.org/W2161872510","https://openalex.org/W2172158418","https://openalex.org/W2172968643","https://openalex.org/W2744055297","https://openalex.org/W3005581722","https://openalex.org/W4211008118","https://openalex.org/W4214717370","https://openalex.org/W4231226883","https://openalex.org/W6640290305","https://openalex.org/W6653435097","https://openalex.org/W6742728668"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"A":[0],"summary":[1],"of":[2,13,35],"the":[3,23,94,97],"state-of-the-art":[4,55],"reinforcement":[5,36,57],"learning":[6,37,58],"in":[7,11,26,85,101],"robotics":[8,27],"is":[9,60],"given,":[10],"terms":[12],"both":[14,52],"algorithms":[15],"and":[16,45,68,91,96],"policy":[17,24,64,76,86],"representations.":[18],"Numerous":[19],"challenges":[20,84],"faced":[21],"by":[22],"representation":[25],"are":[28,40,66,104],"identified.":[29],"Two":[30],"recent":[31],"examples":[32,103],"for":[33,70],"application":[34],"to":[38,81],"robots":[39],"described:":[41],"pancake":[42],"flipping":[43],"task":[44],"bipedal":[46],"walking":[47],"energy":[48],"minimization":[49],"task.":[50,72],"In":[51],"examples,":[53],"a":[54],"Expectation-Maximization-based":[56],"algorithm":[59],"used,":[61],"but":[62],"different":[63],"representations":[65,77],"proposed":[67,75],"evaluated":[69],"each":[71],"The":[73],"two":[74],"offer":[78],"viable":[79],"solutions":[80],"four":[82],"rarely-addressed":[83],"representations:":[87],"correlations,":[88],"adaptability,":[89],"multi-resolution,":[90],"globality.":[92],"Both":[93],"successes":[95],"practical":[98],"difficulties":[99],"encountered":[100],"these":[102],"discussed.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}