{"id":"https://openalex.org/W3161634385","doi":"https://doi.org/10.1007/s10994-021-05982-z","title":"Grounded action transformation for sim-to-real reinforcement learning","display_name":"Grounded action transformation for sim-to-real reinforcement learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161634385","doi":"https://doi.org/10.1007/s10994-021-05982-z","mag":"3161634385"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-021-05982-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-05982-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05982-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05982-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008014974","display_name":"Josiah P. Hanna","orcid":"https://orcid.org/0000-0002-7411-0398"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Josiah P. Hanna","raw_affiliation_strings":["School of Informatics, The University of Edinburgh, Edinburgh, UK"],"raw_orcid":"https://orcid.org/0000-0002-7411-0398","affiliations":[{"raw_affiliation_string":"School of Informatics, The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064607290","display_name":"Siddharth Desai","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Desai","raw_affiliation_strings":["Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039434686","display_name":"Haresh Karnan","orcid":"https://orcid.org/0000-0001-9855-0921"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haresh Karnan","raw_affiliation_strings":["Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060981901","display_name":"Garrett Warnell","orcid":"https://orcid.org/0000-0003-3846-8787"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garrett Warnell","raw_affiliation_strings":["Army Research Laboratory and the Department of Computer Science, The University of Texas at Austin, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Research Laboratory and the Department of Computer Science, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001594330","display_name":"Peter Stone","orcid":"https://orcid.org/0000-0002-6795-420X"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Stone","raw_affiliation_strings":["Department of Computer Science, The University of Texas at Austin and Sony AI, Austin, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin and Sony AI, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008014974"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":2.2779,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.87668473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"110","issue":"9","first_page":"2469","last_page":"2499"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9908999800682068,"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":0.9908999800682068,"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":0.9828000068664551,"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":0.9825000166893005,"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":0.8970829248428345},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6490129232406616},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5713392496109009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5538833141326904},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.49862170219421387},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49425387382507324},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.48474594950675964},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.48221099376678467},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.435534805059433},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4169740080833435}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8970829248428345},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6490129232406616},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5713392496109009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5538833141326904},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.49862170219421387},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49425387382507324},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.48474594950675964},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.48221099376678467},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.435534805059433},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4169740080833435},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"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:10.1007/s10994-021-05982-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-05982-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05982-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-021-05982-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-021-05982-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-021-05982-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2136314175","display_name":null,"funder_award_id":"W911NF-19-2-0333","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G3609089545","display_name":null,"funder_award_id":"N00014-18-2243","funder_id":"https://openalex.org/F4320310620","funder_display_name":"University of Texas at Austin"},{"id":"https://openalex.org/G3694786146","display_name":null,"funder_award_id":"CPS-1739964","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3881771821","display_name":null,"funder_award_id":"N00014-18-2243","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4160581209","display_name":null,"funder_award_id":"NRI-1925082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5029475413","display_name":null,"funder_award_id":"IIS-1724157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G608057831","display_name":null,"funder_award_id":"W911NF-19","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G630961297","display_name":"NRI: FND: Improving Robot Learning from Feedback  and Demonstration using Natural Language","funder_award_id":"1925082","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7861584084","display_name":null,"funder_award_id":"RFP2-000","funder_id":"https://openalex.org/F4320317463","funder_display_name":"Future of Life Institute"},{"id":"https://openalex.org/G8081156953","display_name":"CPS: Medium: Collaborative Research: Synergy: Augmented reality for control of reservation-based intersections with mixed autonomous-non autonomous flows","funder_award_id":"1739964","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G829377574","display_name":"S&AS: INT: Socially-Aware Autonomy for Long-Term Deployment of Always-On Heterogeneous Robot Teams","funder_award_id":"1724157","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8415477955","display_name":null,"funder_award_id":"W911NF-19","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8828030238","display_name":null,"funder_award_id":"W911NF-19-2-0333","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306994","display_name":"Lockheed Martin","ror":"https://ror.org/026er9r08"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320313876","display_name":"Robert Bosch (Australia) Pty","ror":null},{"id":"https://openalex.org/F4320317463","display_name":"Future of Life Institute","ror":null},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3161634385.pdf","grobid_xml":"https://content.openalex.org/works/W3161634385.grobid-xml"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1455277115","https://openalex.org/W1481659984","https://openalex.org/W1587009522","https://openalex.org/W1738827650","https://openalex.org/W1931877416","https://openalex.org/W1977655452","https://openalex.org/W1994030467","https://openalex.org/W2042520683","https://openalex.org/W2081329272","https://openalex.org/W2089087399","https://openalex.org/W2105143952","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2132602063","https://openalex.org/W2138537392","https://openalex.org/W2140135625","https://openalex.org/W2173248099","https://openalex.org/W2174364281","https://openalex.org/W2258540759","https://openalex.org/W2529477964","https://openalex.org/W2530944449","https://openalex.org/W2543474074","https://openalex.org/W2592857946","https://openalex.org/W2605102758","https://openalex.org/W2615735215","https://openalex.org/W2758688321","https://openalex.org/W2767050701","https://openalex.org/W2801572960","https://openalex.org/W2898758998","https://openalex.org/W2899460553","https://openalex.org/W2947469668","https://openalex.org/W2948443723","https://openalex.org/W2949608212","https://openalex.org/W2952629144","https://openalex.org/W2952765942","https://openalex.org/W2962837436","https://openalex.org/W2962899390","https://openalex.org/W2962957005","https://openalex.org/W2962957031","https://openalex.org/W2963184939","https://openalex.org/W2963390419","https://openalex.org/W2963677339","https://openalex.org/W2963906246","https://openalex.org/W2964198579","https://openalex.org/W2964214518","https://openalex.org/W2964262254","https://openalex.org/W2968116426","https://openalex.org/W2969591498","https://openalex.org/W2990747716","https://openalex.org/W3003669699","https://openalex.org/W3101442004","https://openalex.org/W3146158996","https://openalex.org/W4214717370","https://openalex.org/W4248967795","https://openalex.org/W6638018090","https://openalex.org/W6644813291","https://openalex.org/W6728925229","https://openalex.org/W6735677848","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning":[2,16,41,98,134,227,235],"in":[3,17,24,69,109,120,148,206,242],"simulation":[4,25,40,121,226],"is":[5,45],"a":[6,46,86,102,135,140,145,154,214,221],"promising":[7],"alternative":[8],"to":[9,51,59,97,116,122,124,133,153,187,201,212,220,236],"the":[10,18,35,57,62,72,125,173,188],"prohibitive":[11],"sample":[12],"cost":[13],"of":[14,71,224],"reinforcement":[15,234],"physical":[19,37],"world.":[20,127],"Unfortunately,":[21],"policies":[22,31,100,118,240],"learned":[23,119],"often":[26],"perform":[27],"worse":[28],"than":[29],"hand-coded":[30,157],"when":[32,172],"applied":[33],"on":[34,76,139],"target,":[36],"system.":[38],"Grounded":[39],"(":[42,191],"gsl":[43,90],")":[44,193],"general":[47],"framework":[48],"that":[49,168,198],"promises":[50],"address":[52,181],"this":[53,182],"issue":[54],"by":[55],"altering":[56],"simulator":[58],"better":[60],"match":[61],"real":[63,126,174,203],"world":[64,175,204],"(Farchy":[65],"et":[66],"al.":[67],"2013":[68],"Proceedings":[70],"12th":[73],"international":[74],"conference":[75],"autonomous":[77],"agents":[78],"and":[79,143,195,228],"multiagent":[80],"systems":[81],"(AAMAS)).":[82],"This":[83,159],"article":[84],"introduces":[85],"new":[87],"algorithm":[88,108,132,194],"for":[89,101,232],"\u2014Grounded":[91],"Action":[92],"Transformation":[93],"(GAT)\u2014and":[94],"applies":[95],"it":[96,115],"control":[99,239],"humanoid":[103,141],"robot.":[104],"We":[105,128],"evaluate":[106],"our":[107,131],"controlled":[110],"experiments":[111],"where":[112,208],"we":[113,184],"show":[114,197],"allow":[117],"transfer":[123,205],"then":[129],"apply":[130],"fast":[136],"bipedal":[137],"walk":[138,150],"robot":[142,238],"demonstrate":[144,229],"43.27%":[146],"improvement":[147],"forward":[149],"velocity":[151],"compared":[152],"state-of-the":[155],"art":[156],"walk.":[158],"striking":[160],"empirical":[161,165],"success":[162],"notwithstanding,":[163],"further":[164],"analysis":[166],"shows":[167],"gat":[169,186,190,209],"may":[170,210],"struggle":[171],"has":[176],"stochastic":[177,189],"state":[178],"transitions.":[179],"To":[180],"limitation":[183],"generalize":[185],"sgat":[192,199],"empirically":[196],"leads":[200],"successful":[202],"situations":[207],"fail":[211],"find":[213],"good":[215],"policy.":[216],"Our":[217],"results":[218],"contribute":[219],"deeper":[222],"understanding":[223],"grounded":[225],"its":[230],"effectiveness":[231],"applying":[233],"learn":[237],"entirely":[241],"simulation.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}