{"id":"https://openalex.org/W2792036039","doi":"https://doi.org/10.1109/iros.2018.8593894","title":"Setting up a Reinforcement Learning Task with a Real-World Robot","display_name":"Setting up a Reinforcement Learning Task with a Real-World Robot","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2792036039","doi":"https://doi.org/10.1109/iros.2018.8593894","mag":"2792036039"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.07067","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102815213","display_name":"A. Rupam Mahmood","orcid":"https://orcid.org/0000-0002-2640-1844"},"institutions":[{"id":"https://openalex.org/I3129744201","display_name":"University of Kindu","ror":"https://ror.org/03k1g6m92","country_code":"CD","type":"education","lineage":["https://openalex.org/I3129744201"]}],"countries":["CD"],"is_corresponding":true,"raw_author_name":"A. Rupam Mahmood","raw_affiliation_strings":["Kindred Inc"],"affiliations":[{"raw_affiliation_string":"Kindred Inc","institution_ids":["https://openalex.org/I3129744201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058918505","display_name":"Dmytro Korenkevych","orcid":"https://orcid.org/0009-0007-5748-9571"},"institutions":[{"id":"https://openalex.org/I3129744201","display_name":"University of Kindu","ror":"https://ror.org/03k1g6m92","country_code":"CD","type":"education","lineage":["https://openalex.org/I3129744201"]}],"countries":["CD"],"is_corresponding":false,"raw_author_name":"Dmytro Korenkevych","raw_affiliation_strings":["Kindred Inc"],"affiliations":[{"raw_affiliation_string":"Kindred Inc","institution_ids":["https://openalex.org/I3129744201"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041027747","display_name":"Brent Komer","orcid":null},"institutions":[{"id":"https://openalex.org/I3129744201","display_name":"University of Kindu","ror":"https://ror.org/03k1g6m92","country_code":"CD","type":"education","lineage":["https://openalex.org/I3129744201"]}],"countries":["CD"],"is_corresponding":false,"raw_author_name":"Brent J. Komer","raw_affiliation_strings":["Kindred Inc"],"affiliations":[{"raw_affiliation_string":"Kindred Inc","institution_ids":["https://openalex.org/I3129744201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057264590","display_name":"James Bergstra","orcid":null},"institutions":[{"id":"https://openalex.org/I3129744201","display_name":"University of Kindu","ror":"https://ror.org/03k1g6m92","country_code":"CD","type":"education","lineage":["https://openalex.org/I3129744201"]}],"countries":["CD"],"is_corresponding":false,"raw_author_name":"James Bergstra","raw_affiliation_strings":["Kindred Inc"],"affiliations":[{"raw_affiliation_string":"Kindred Inc","institution_ids":["https://openalex.org/I3129744201"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102815213"],"corresponding_institution_ids":["https://openalex.org/I3129744201"],"apc_list":null,"apc_paid":null,"fwci":2.9317,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.927736,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4635","last_page":"4640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965000152587891,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9804999828338623,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8979377746582031},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7781140208244324},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7409490346908569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6840896606445312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.534682035446167},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5304151177406311},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5136582255363464},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.47400176525115967},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43680620193481445},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33542418479919434},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.17659321427345276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1606767773628235},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.1097927987575531},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10096704959869385}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8979377746582031},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7781140208244324},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7409490346908569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840896606445312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534682035446167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5304151177406311},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5136582255363464},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.47400176525115967},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43680620193481445},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33542418479919434},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.17659321427345276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1606767773628235},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.1097927987575531},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10096704959869385},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros.2018.8593894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593894","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1803.07067","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.07067","pdf_url":"https://arxiv.org/pdf/1803.07067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2792036039","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.07067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1803.07067","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1803.07067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1803.07067","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1803.07067","pdf_url":"https://arxiv.org/pdf/1803.07067","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2792036039.pdf","grobid_xml":"https://content.openalex.org/works/W2792036039.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W40338364","https://openalex.org/W1984120922","https://openalex.org/W2024390895","https://openalex.org/W2060914855","https://openalex.org/W2097797606","https://openalex.org/W2117864026","https://openalex.org/W2158782408","https://openalex.org/W2159566498","https://openalex.org/W2342662072","https://openalex.org/W2529658650","https://openalex.org/W2575705757","https://openalex.org/W2754517384","https://openalex.org/W2949608212","https://openalex.org/W2952629144","https://openalex.org/W3037207827","https://openalex.org/W6638018090","https://openalex.org/W6674385629","https://openalex.org/W6682849425","https://openalex.org/W6704571135","https://openalex.org/W6728925229"],"related_works":["https://openalex.org/W2964227158","https://openalex.org/W2145339207","https://openalex.org/W2964161785","https://openalex.org/W2173248099","https://openalex.org/W2890803796","https://openalex.org/W2114882146","https://openalex.org/W2995058766","https://openalex.org/W2996556441","https://openalex.org/W3087903566","https://openalex.org/W2575705757","https://openalex.org/W3127556163","https://openalex.org/W50296447","https://openalex.org/W3203679646","https://openalex.org/W2589275886","https://openalex.org/W3206200647","https://openalex.org/W2973019294","https://openalex.org/W3138680551","https://openalex.org/W3023334751","https://openalex.org/W1832605823","https://openalex.org/W2124695578"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,18,35,49,59,110,169],"is":[2,22,39],"a":[3,58,62,74],"promising":[4],"approach":[5],"to":[6,66,68,81,116,142],"developing":[7],"hard-to-engineer":[8],"adaptive":[9],"solutions":[10],"for":[11,46],"complex":[12],"and":[13,25,77,97,119,122,132,148,155],"diverse":[14],"robotic":[15,64],"tasks.":[16],"However,":[17],"with":[19,51,61,84],"real-world":[20,174],"robots":[21,85],"often":[23],"unreliable":[24],"difficult,":[26],"which":[27],"resulted":[28],"in":[29,33,124,161],"their":[30,79],"low":[31],"adoption":[32],"reinforcement":[34,168],"research.":[36],"This":[37],"difficulty":[38],"worsened":[40],"by":[41],"the":[42,82,95,98,102,117,165],"lack":[43],"of":[44,73,94,167],"guidelines":[45],"setting":[47],"up":[48],"tasks":[50],"robots.":[52,175],"In":[53],"this":[54],"work,":[55],"we":[56],"develop":[57],"task":[60,75,96],"UR5":[63],"arm":[65],"bring":[67],"light":[69],"some":[70,139],"key":[71],"elements":[72],"setup":[76,103,125],"study":[78,137],"contributions":[80],"challenges":[83],"<sup":[86,89],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[87,90],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[88,91],"Source":[92],"code":[93],"computational":[99],"model":[100],"behind":[101],"available":[104],"at":[105],"https://github.com/kindredresearch/SenseAct.":[106],"We":[107,150],"find":[108],"that":[109,152],"performance":[111],"can":[112,127,158],"be":[113,159],"highly":[114,153],"sensitive":[115],"setup,":[118,163],"thus":[120],"oversights":[121],"omissions":[123],"details":[126],"make":[128],"effective":[129],"learning,":[130],"reproducibility,":[131],"fair":[133],"comparison":[134],"hard.":[135],"Our":[136],"suggests":[138],"mitigating":[140],"steps":[141],"help":[143],"future":[144],"experimenters":[145],"avoid":[146],"difficulties":[147],"pitfalls.":[149],"show":[151],"reliable":[154],"repeatable":[156],"experiments":[157],"performed":[160],"our":[162],"indicating":[164],"possibility":[166],"research":[170],"extensively":[171],"based":[172],"on":[173]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5}],"updated_date":"2026-02-24T19:35:01.260952","created_date":"2025-10-10T00:00:00"}