{"id":"https://openalex.org/W2962983251","doi":"https://doi.org/10.1109/roman.2018.8525631","title":"Smooth and Efficient Policy Exploration for Robot Trajectory Learning","display_name":"Smooth and Efficient Policy Exploration for Robot Trajectory Learning","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2962983251","doi":"https://doi.org/10.1109/roman.2018.8525631","mag":"2962983251"},"language":"en","primary_location":{"id":"doi:10.1109/roman.2018.8525631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2018.8525631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","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/A5022096464","display_name":"Shidi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I160977438","display_name":"West Ukrainian National University","ror":"https://ror.org/047988g19","country_code":"UA","type":"education","lineage":["https://openalex.org/I160977438"]}],"countries":["UA"],"is_corresponding":false,"raw_author_name":"Shidi Li","raw_affiliation_strings":["Research Institute for Intelligent Computer Systems, Ternopil National Economic University, Ternopil, Ukraine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Intelligent Computer Systems, Ternopil National Economic University, Ternopil, Ukraine","institution_ids":["https://openalex.org/I160977438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073468340","display_name":"Chee\u2013Meng Chew","orcid":"https://orcid.org/0000-0002-6396-4371"},"institutions":[{"id":"https://openalex.org/I283429734","display_name":"Kazimierz Pu\u0142aski University of Technology and Humanities in Radom","ror":"https://ror.org/01f4dr878","country_code":"PL","type":"education","lineage":["https://openalex.org/I283429734"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Chee-Meng Chew","raw_affiliation_strings":["Department of Informatics, Kazimierz Pulaski University of Technology and Humaities in Radom, Radom, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Kazimierz Pulaski University of Technology and Humaities in Radom, Radom, Poland","institution_ids":["https://openalex.org/I283429734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055514220","display_name":"Velusamy Subramaniam","orcid":null},"institutions":[{"id":"https://openalex.org/I160977438","display_name":"West Ukrainian National University","ror":"https://ror.org/047988g19","country_code":"UA","type":"education","lineage":["https://openalex.org/I160977438"]}],"countries":["UA"],"is_corresponding":false,"raw_author_name":"Velusamy Subramaniam","raw_affiliation_strings":["Research Institute for Intelligent Computer Systems, Ternopil National Economic University, Ternopil, Ukraine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Intelligent Computer Systems, Ternopil National Economic University, Ternopil, Ukraine","institution_ids":["https://openalex.org/I160977438"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2264,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56981937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1087","last_page":"1092"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9987999796867371,"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":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.7468671798706055},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.72125244140625},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6756360530853271},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5647169947624207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5536832213401794},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.4568536877632141},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32602035999298096},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11136060953140259}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7468671798706055},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.72125244140625},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6756360530853271},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5647169947624207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5536832213401794},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.4568536877632141},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32602035999298096},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11136060953140259},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/roman.2018.8525631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/roman.2018.8525631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1967859677","https://openalex.org/W1977655452","https://openalex.org/W1986014385","https://openalex.org/W2012392077","https://openalex.org/W2016765487","https://openalex.org/W2019965290","https://openalex.org/W2042882799","https://openalex.org/W2100235553","https://openalex.org/W2119717200","https://openalex.org/W2123327324","https://openalex.org/W2136719407","https://openalex.org/W2142383762","https://openalex.org/W2161395589","https://openalex.org/W2172158418","https://openalex.org/W2529601334","https://openalex.org/W2563595373","https://openalex.org/W2591436094","https://openalex.org/W2737943148","https://openalex.org/W6653435097","https://openalex.org/W6680987236"],"related_works":["https://openalex.org/W3198113463","https://openalex.org/W4285827128","https://openalex.org/W2602382373","https://openalex.org/W2787698406","https://openalex.org/W2963844355","https://openalex.org/W2903025760","https://openalex.org/W4361251046","https://openalex.org/W4301772239","https://openalex.org/W3095116576","https://openalex.org/W98577079"],"abstract_inverted_index":{"Many":[0],"policy":[1],"search":[2],"algorithms":[3],"have":[4],"been":[5],"proposed":[6,82],"for":[7,88],"robot":[8,17,90],"learning":[9,66,128],"and":[10,97],"proved":[11],"to":[12,39,54,68],"be":[13,49,92],"practical":[14],"in":[15,24,56,114],"real":[16,58],"applications.":[18],"However,":[19],"there":[20],"are":[21],"still":[22],"hyperparameters":[23],"the":[25,29,41,57,70,89,95,98,103,107,115,126,131],"algorithms,":[26],"such":[27],"as":[28,130],"exploration":[30,42,71,100],"rate,":[31],"which":[32],"requires":[33],"manual":[34],"tuning.":[35],"The":[36,74,118],"existing":[37],"methods":[38,81,133],"design":[40],"rate":[43,72,101],"manually":[44],"or":[45,52],"automatically":[46],"may":[47],"not":[48],"general":[50],"enough":[51],"hard":[53],"apply":[55],"robot.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"a":[65,78],"model":[67],"update":[69],"adaptively.":[73],"overall":[75],"algorithm":[76,96],"is":[77,112],"combination":[79],"of":[80,106],"by":[83,94],"other":[84],"researchers.":[85],"Smooth":[86],"trajectories":[87],"can":[91,124],"produced":[93],"updated":[99],"maximizes":[102],"lower":[104],"bound":[105],"expected":[108],"return.":[109],"Our":[110],"method":[111,123],"tested":[113],"ball-in-cup":[116],"problem.":[117],"results":[119],"show":[120],"that":[121],"our":[122],"receive":[125],"same":[127],"outcome":[129],"previous":[132],"but":[134],"with":[135],"fewer":[136],"iterations.":[137]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}