{"id":"https://openalex.org/W3009584224","doi":"https://doi.org/10.1109/lars-sbr-wre48964.2019.00060","title":"Sim-to-Real in Reinforcement Learning for Everyone","display_name":"Sim-to-Real in Reinforcement Learning for Everyone","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3009584224","doi":"https://doi.org/10.1109/lars-sbr-wre48964.2019.00060","mag":"3009584224"},"language":"en","primary_location":{"id":"doi:10.1109/lars-sbr-wre48964.2019.00060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars-sbr-wre48964.2019.00060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Latin American Robotics Symposium (LARS), 2019 Brazilian Symposium on Robotics (SBR) and 2019 Workshop on Robotics in Education (WRE)","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/A5042061869","display_name":"Juliano Vacaro","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Juliano Vacaro","raw_affiliation_strings":["HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108381593","display_name":"Guilherme Marques","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guilherme Marques","raw_affiliation_strings":["HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112527120","display_name":"Bruna Oliveira","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bruna Oliveira","raw_affiliation_strings":["HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025465515","display_name":"Gabriel Andrade Paz","orcid":"https://orcid.org/0000-0001-8474-9753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gabriel Paz","raw_affiliation_strings":["HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077014408","display_name":"Thomas Paula","orcid":"https://orcid.org/0000-0002-3815-9135"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Paula","raw_affiliation_strings":["HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002631284","display_name":"Wagston Staehler","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wagston Staehler","raw_affiliation_strings":["HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil"],"affiliations":[{"raw_affiliation_string":"HP Labs (AIECL), Porto Alegre, Rio Grande do Sul, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079006038","display_name":"David Murphy","orcid":"https://orcid.org/0000-0003-1889-0091"},"institutions":[{"id":"https://openalex.org/I1324840837","display_name":"Hewlett-Packard (United States)","ror":"https://ror.org/059rn9488","country_code":"US","type":"company","lineage":["https://openalex.org/I1324840837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Murphy","raw_affiliation_strings":["HP Labs (AIECL), Palo Alto, California, USA"],"affiliations":[{"raw_affiliation_string":"HP Labs (AIECL), Palo Alto, California, USA","institution_ids":["https://openalex.org/I1324840837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5042061869"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.14,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.6040768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"310"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.98580002784729,"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":0.863247811794281},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7466844916343689},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5912144184112549},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.583869457244873},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5384284257888794},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.49232208728790283},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4554729759693146},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.42940694093704224},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4293852150440216},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3360888659954071},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09588268399238586},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08491203188896179}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.863247811794281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7466844916343689},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5912144184112549},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.583869457244873},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5384284257888794},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.49232208728790283},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4554729759693146},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.42940694093704224},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4293852150440216},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3360888659954071},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09588268399238586},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08491203188896179},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lars-sbr-wre48964.2019.00060","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lars-sbr-wre48964.2019.00060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Latin American Robotics Symposium (LARS), 2019 Brazilian Symposium on Robotics (SBR) and 2019 Workshop on Robotics in Education (WRE)","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":24,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2534269850","https://openalex.org/W2605102758","https://openalex.org/W2745868649","https://openalex.org/W2754517384","https://openalex.org/W2889987506","https://openalex.org/W2919115771","https://openalex.org/W2952629144","https://openalex.org/W2962867954","https://openalex.org/W2963390419","https://openalex.org/W2963985863","https://openalex.org/W3037207827","https://openalex.org/W3100789280","https://openalex.org/W4295719664","https://openalex.org/W4297797010","https://openalex.org/W6728925229","https://openalex.org/W6744123322","https://openalex.org/W6745935785","https://openalex.org/W6748638692","https://openalex.org/W6753526802","https://openalex.org/W6757358677","https://openalex.org/W6780225908"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"In":[0,27],"reinforcement":[1],"learning":[2],"(RL),":[3],"it":[4,22,130],"remains":[5],"a":[6,10,14,35,44,51,81,91,118],"challenge":[7],"to":[8,41,62,98,120,131,139,159,183,203],"have":[9],"robotic":[11,37],"agent":[12],"perform":[13],"task":[15],"in":[16,25,39,47,54,85,90,96,111,143,187],"the":[17,60,63,68,73,77,100,105,108,112,122,126,132,144,160,185,188,195,199,204],"real":[18,64,113,161,189],"world":[19],"for":[20,134],"which":[21,136],"was":[23],"trained":[24,109],"simulation.":[26],"this":[28],"paper,":[29],"we":[30],"present":[31],"our":[32],"work":[33,148],"training":[34,79,153],"low-cost":[36],"arm":[38],"simulation":[40,86],"move":[42],"towards":[43],"predefined":[45],"target":[46],"space,":[48],"represented":[49],"by":[50,167,177],"red":[52],"ball":[53],"an":[55],"RGB":[56],"image,":[57],"and":[58,103,156],"transferring":[59],"capability":[61],"arm.":[65],"We":[66,115],"exercised":[67],"entire":[69],"end-to-end":[70],"flow":[71],"including":[72],"3D":[74],"modeling":[75],"of":[76,80,107,152,179],"arm,":[78],"state-of-the-art":[82],"RL":[83,154],"policy":[84],"with":[87],"multiple":[88],"actors":[89],"distributed":[92],"fashion,":[93],"domain":[94],"randomization":[95],"order":[97],"close":[99],"sim-to-real":[101],"gap,":[102],"finally":[104],"execution":[106],"model":[110,133],"robot.":[114],"also":[116],"implemented":[117],"mechanism":[119],"edit":[121],"image":[123],"captured":[124],"from":[125],"camera":[127],"before":[128],"sending":[129],"inference,":[135],"allowed":[137],"us":[138],"automate":[140],"reward":[141,186],"computation":[142],"physical":[145],"world.":[146],"Our":[147],"highlights":[149],"important":[150,164],"challenges":[151],"agents":[155],"moving":[157],"them":[158,180],"world,":[162],"validating":[163],"aspects":[165],"shown":[166],"other":[168],"works":[169],"as":[170,172,198],"well":[171],"detailing":[173],"steps":[174],"not":[175],"explained":[176],"some":[178],"(e.g.":[181],"how":[182],"compute":[184],"world).":[190],"The":[191],"conducted":[192],"experiments":[193],"show":[194],"improvements":[196],"observed":[197],"techniques":[200],"were":[201],"added":[202],"final":[205],"solution.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
