{"id":"https://openalex.org/W4313306842","doi":"https://doi.org/10.1109/iccais56082.2022.9990480","title":"Sample-Efficient Reinforcement Learning for Pose Regulation of a Mobile Robot","display_name":"Sample-Efficient Reinforcement Learning for Pose Regulation of a Mobile Robot","publication_year":2022,"publication_date":"2022-11-21","ids":{"openalex":"https://openalex.org/W4313306842","doi":"https://doi.org/10.1109/iccais56082.2022.9990480"},"language":"en","primary_location":{"id":"doi:10.1109/iccais56082.2022.9990480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais56082.2022.9990480","pdf_url":null,"source":{"id":"https://openalex.org/S4363608617","display_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","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/A5089377677","display_name":"Walter Brescia","orcid":"https://orcid.org/0009-0000-9943-3727"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Walter Brescia","raw_affiliation_strings":["Politecnico di Bari,Bari,Italy","Politecnico di Bari, Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Bari,Bari,Italy","institution_ids":["https://openalex.org/I68618741"]},{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028924887","display_name":"Luca De Cicco","orcid":"https://orcid.org/0000-0002-8900-175X"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca De Cicco","raw_affiliation_strings":["Politecnico di Bari,Bari,Italy","Politecnico di Bari, Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Bari,Bari,Italy","institution_ids":["https://openalex.org/I68618741"]},{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010345083","display_name":"Saverio Mascolo","orcid":"https://orcid.org/0000-0001-9686-5532"},"institutions":[{"id":"https://openalex.org/I68618741","display_name":"Polytechnic University of Bari","ror":"https://ror.org/03c44v465","country_code":"IT","type":"education","lineage":["https://openalex.org/I68618741"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Saverio Mascolo","raw_affiliation_strings":["Politecnico di Bari,Bari,Italy","Politecnico di Bari, Bari, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Bari,Bari,Italy","institution_ids":["https://openalex.org/I68618741"]},{"raw_affiliation_string":"Politecnico di Bari, Bari, Italy","institution_ids":["https://openalex.org/I68618741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I68618741"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18328148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"47"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8604010343551636},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6974912285804749},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6868715882301331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6596812009811401},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.48080721497535706},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4667853116989136},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44253015518188477},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42809751629829407}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8604010343551636},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6974912285804749},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6868715882301331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596812009811401},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48080721497535706},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4667853116989136},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44253015518188477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42809751629829407},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais56082.2022.9990480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais56082.2022.9990480","pdf_url":null,"source":{"id":"https://openalex.org/S4363608617","display_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 11th International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2092695017","https://openalex.org/W2114897272","https://openalex.org/W2296073425","https://openalex.org/W2736601468","https://openalex.org/W2758919913","https://openalex.org/W2949924544","https://openalex.org/W2982554184","https://openalex.org/W3011706575","https://openalex.org/W3104734738","https://openalex.org/W3169363132","https://openalex.org/W3178845376","https://openalex.org/W4297913451","https://openalex.org/W6621543089","https://openalex.org/W6684921986","https://openalex.org/W6734655788","https://openalex.org/W6737937804","https://openalex.org/W6780559895","https://openalex.org/W6796791731"],"related_works":["https://openalex.org/W2122871747","https://openalex.org/W2607437843","https://openalex.org/W3114279067","https://openalex.org/W4295700147","https://openalex.org/W2963162727","https://openalex.org/W2877093712","https://openalex.org/W2116157560","https://openalex.org/W2106714532","https://openalex.org/W4297979791","https://openalex.org/W4310614650"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"has":[3],"gained":[4],"interest":[5],"in":[6,17,43,95,152],"the":[7,27,31,84,96,102,110,116],"control":[8,20,63],"and":[9,29,81,101],"automation":[10],"communities":[11],"thanks":[12],"to":[13,58,60,77,109],"its":[14],"encouraging":[15],"results":[16],"many":[18],"challenging":[19],"problems":[21],"without":[22],"requiring":[23],"a":[24,40,50,70,123,128,138,154],"model":[25],"of":[26,30,53,91,118,127,141,150],"system":[28],"environment.":[32],"Yet,":[33],"it":[34],"is":[35],"well-known":[36],"that":[37,87,105],"employing":[38],"such":[39,119],"learning-based":[41],"approach":[42],"real":[44],"scenarios":[45],"may":[46],"be":[47,56],"problematic,":[48],"as":[49],"prohibitive":[51],"amount":[52],"data":[54],"might":[55],"required":[57],"converge":[59],"an":[61],"optimal":[62],"policy.":[64],"In":[65],"this":[66],"work,":[67],"we":[68],"equip":[69],"popular":[71],"RL":[72],"algorithm":[73],"with":[74],"two":[75],"tools":[76,121],"improve":[78],"exploration":[79],"effectiveness":[80,117],"sample":[82],"efficiency:":[83],"Episodic":[85],"Noise,":[86],"helps":[88],"useful":[89],"subsets":[90],"actions":[92,151],"emerge":[93],"already":[94],"first":[97],"few":[98,155],"training":[99,157],"episodes,":[100],"Difficulty":[103],"Manager,":[104],"generates":[106],"goals":[107],"proportioned":[108],"current":[111],"agent\u2019s":[112],"capabilities.":[113],"We":[114],"demonstrate":[115],"proposed":[120],"on":[122],"pose":[124],"regulation":[125],"task":[126],"four":[129,132],"wheel":[130,133],"steering":[131],"driving":[134],"robot,":[135],"suitable":[136],"for":[137],"wide":[139],"range":[140],"industrial":[142],"scenarios.":[143],"The":[144],"resulting":[145],"agent":[146],"learns":[147],"effective":[148],"sets":[149],"just":[153],"hundreds":[156],"epochs,":[158],"reaching":[159],"satisfactory":[160],"performance":[161],"during":[162],"tests.":[163]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}