{"id":"https://openalex.org/W3040490156","doi":"https://doi.org/10.15607/rss.2020.xvi.076","title":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","display_name":"Scaling data-driven robotics with reward sketching and batch reinforcement learning","publication_year":2020,"publication_date":"2020-06-30","ids":{"openalex":"https://openalex.org/W3040490156","doi":"https://doi.org/10.15607/rss.2020.xvi.076","mag":"3040490156"},"language":"en","primary_location":{"id":"doi:10.15607/rss.2020.xvi.076","is_oa":false,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XVI","raw_type":"proceedings-article"},"type":"preprint","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/A5007394281","display_name":"Serkan Cabi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Serkan Cabi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073651612","display_name":"Sergio G\u00f3mez Colmenarejo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergio G\u00f3mez Colmenarejo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101733096","display_name":"Alexander Novikov","orcid":"https://orcid.org/0000-0001-8529-173X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Novikov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074807706","display_name":"Ksenia Konyushova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ksenia Konyushova","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059110895","display_name":"Scott Reed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Scott Reed","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079341248","display_name":"Rae Jeong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rae Jeong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032140556","display_name":"Konrad \u017bo\u0142na","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Konrad Zolna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056410851","display_name":"Yusuf Aytar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuf Aytar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003238807","display_name":"David Budden","orcid":"https://orcid.org/0000-0003-4372-8985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Budden","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032877928","display_name":"Mel Vecer\u00edk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mel Vecerik","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061512729","display_name":"Oleg Sushkov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleg Sushkov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108639255","display_name":"David Barker","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Barker","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077984643","display_name":"Jonathan Scholz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Scholz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008260665","display_name":"Misha Denil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Misha Denil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082304130","display_name":"Nando de Freitas","orcid":"https://orcid.org/0000-0003-4770-7217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nando de Freitas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100420910","display_name":"Ziyu Wang","orcid":"https://orcid.org/0000-0001-9534-3134"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":16,"corresponding_author_ids":["https://openalex.org/A5007394281"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.15501403,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97031211,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9980000257492065,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.98089998960495,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8131458163261414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6805285215377808},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6443992853164673},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6258454918861389},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6133896708488464},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4695361852645874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41450047492980957},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3119361102581024},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18508246541023254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1436712145805359}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8131458163261414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6805285215377808},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6443992853164673},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6258454918861389},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6133896708488464},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4695361852645874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41450047492980957},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3119361102581024},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18508246541023254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1436712145805359},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15607/rss.2020.xvi.076","is_oa":false,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics: Science and Systems XVI","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4233452137","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4254857216","https://openalex.org/W405964254","https://openalex.org/W4295941380","https://openalex.org/W2045758229","https://openalex.org/W4319083788"],"abstract_inverted_index":{"We":[0,27,111],"present":[1],"a":[2,11,42,49,58,68,94,104,125],"framework":[3,33],"for":[4],"data-driven":[5],"robotics":[6],"that":[7,113],"makes":[8],"use":[9,57],"of":[10,14,48,61,97,127],"large":[12,95],"dataset":[13,96],"recorded":[15,54],"robot":[16,44,105],"experience":[17,98],"and":[18,135],"scales":[19],"to":[20,30,34,66,74,102,120,123],"several":[21],"tasks":[22,40,78,101,130],"using":[23,108,114],"learned":[24],"reward":[25,69,81],"functions.":[26],"show":[28,112],"how":[29],"apply":[31],"this":[32],"accomplish":[35],"three":[36],"different":[37,100],"object":[38],"manipulation":[39,129],"on":[41],"real":[43],"platform.":[45],"Given":[46],"demonstrations":[47],"task":[50],"together":[51],"with":[52,76,93],"task-agnostic":[53],"experience,":[55],"we":[56],"special":[59],"form":[60],"human":[62],"annotation":[63],"as":[64],"supervision":[65],"learn":[67,103],"function,":[70],"which":[71],"enables":[72],"us":[73],"deal":[75],"real-world":[77],"where":[79],"the":[80],"signal":[82],"cannot":[83],"be":[84],"acquired":[85],"directly.":[86],"Learned":[87],"rewards":[88],"are":[89],"used":[90],"in":[91],"combination":[92],"from":[99],"policy":[106],"offline":[107],"batch":[109],"RL.":[110],"our":[115],"approach":[116],"it":[117],"is":[118],"possible":[119],"train":[121],"agents":[122],"perform":[124],"variety":[126],"challenging":[128],"including":[131],"stacking":[132],"rigid":[133],"objects":[134],"handling":[136],"cloth.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}