{"id":"https://openalex.org/W3103793864","doi":"https://doi.org/10.1109/icra48506.2021.9560764","title":"Sample-efficient Reinforcement Learning in Robotic Table Tennis","display_name":"Sample-efficient Reinforcement Learning in Robotic Table Tennis","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3103793864","doi":"https://doi.org/10.1109/icra48506.2021.9560764","mag":"3103793864"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9560764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/2011.03275","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009451279","display_name":"Jonas Tebbe","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jonas Tebbe","raw_affiliation_strings":["Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000659764","display_name":"Lukas Krauch","orcid":null},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Krauch","raw_affiliation_strings":["Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066992222","display_name":"Yapeng Gao","orcid":"https://orcid.org/0000-0002-9258-9304"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yapeng Gao","raw_affiliation_strings":["Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076","institution_ids":["https://openalex.org/I8087733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004958444","display_name":"Andreas Zell","orcid":"https://orcid.org/0000-0003-3299-2211"},"institutions":[{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Zell","raw_affiliation_strings":["Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Cognitive Systems Group, University of Tuebingen, Tuebingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"University of Tuebingen,Cognitive Systems Group,Computer Science Department,Tuebingen,Germany,72076","institution_ids":["https://openalex.org/I8087733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009451279"],"corresponding_institution_ids":["https://openalex.org/I8087733"],"apc_list":null,"apc_paid":null,"fwci":0.70551788,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74325788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4171","last_page":"4178"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9905999898910522,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8610155582427979},{"id":"https://openalex.org/keywords/racket","display_name":"Racket","score":0.8001606464385986},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6566765308380127},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6467241048812866},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6385483145713806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521305501461029},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.505012571811676},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.49797487258911133},{"id":"https://openalex.org/keywords/ball","display_name":"Ball (mathematics)","score":0.45589756965637207},{"id":"https://openalex.org/keywords/tennis-ball","display_name":"Tennis ball","score":0.4425842761993408},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.43117061257362366},{"id":"https://openalex.org/keywords/orientation","display_name":"Orientation (vector space)","score":0.412926584482193},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3746769428253174},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13703030347824097},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12990671396255493}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8610155582427979},{"id":"https://openalex.org/C2778707667","wikidata":"https://www.wikidata.org/wiki/Q1254148","display_name":"Racket","level":3,"score":0.8001606464385986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6566765308380127},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6467241048812866},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6385483145713806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521305501461029},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.505012571811676},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.49797487258911133},{"id":"https://openalex.org/C122041747","wikidata":"https://www.wikidata.org/wiki/Q838611","display_name":"Ball (mathematics)","level":2,"score":0.45589756965637207},{"id":"https://openalex.org/C2992174615","wikidata":"https://www.wikidata.org/wiki/Q246514","display_name":"Tennis ball","level":3,"score":0.4425842761993408},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.43117061257362366},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.412926584482193},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3746769428253174},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13703030347824097},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12990671396255493},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.0},{"id":"https://openalex.org/C2780101202","wikidata":"https://www.wikidata.org/wiki/Q768186","display_name":"sports equipment","level":2,"score":0.0},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9560764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9560764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.03275","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.03275","pdf_url":"https://arxiv.org/pdf/2011.03275","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:3103793864","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.03275","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.2011.03275","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.03275","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:2011.03275","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.03275","pdf_url":"https://arxiv.org/pdf/2011.03275","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/W3103793864.pdf","grobid_xml":"https://content.openalex.org/works/W3103793864.grobid-xml"},"referenced_works_count":73,"referenced_works":["https://openalex.org/W745775011","https://openalex.org/W1499669280","https://openalex.org/W1506540549","https://openalex.org/W1771410628","https://openalex.org/W1777239053","https://openalex.org/W1977655452","https://openalex.org/W1983504832","https://openalex.org/W2012204020","https://openalex.org/W2023801472","https://openalex.org/W2064276653","https://openalex.org/W2110307800","https://openalex.org/W2116898904","https://openalex.org/W2145339207","https://openalex.org/W2200431364","https://openalex.org/W2257979135","https://openalex.org/W2385601253","https://openalex.org/W2534269850","https://openalex.org/W2575705757","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2761873684","https://openalex.org/W2767050701","https://openalex.org/W2789008106","https://openalex.org/W2797121477","https://openalex.org/W2811292668","https://openalex.org/W2902690953","https://openalex.org/W2902907165","https://openalex.org/W2905364877","https://openalex.org/W2912622940","https://openalex.org/W2914987759","https://openalex.org/W2946783853","https://openalex.org/W2949676527","https://openalex.org/W2962736495","https://openalex.org/W2962902376","https://openalex.org/W2963099939","https://openalex.org/W2963313316","https://openalex.org/W2963411833","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2964001908","https://openalex.org/W2964043796","https://openalex.org/W2964263543","https://openalex.org/W2964273112","https://openalex.org/W2967727187","https://openalex.org/W2968116426","https://openalex.org/W3013618273","https://openalex.org/W3014969391","https://openalex.org/W3037207827","https://openalex.org/W3037785630","https://openalex.org/W3090503027","https://openalex.org/W3101442004","https://openalex.org/W3131531515","https://openalex.org/W6622050690","https://openalex.org/W6638018090","https://openalex.org/W6638088447","https://openalex.org/W6683397050","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6728925229","https://openalex.org/W6739585900","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6742461812","https://openalex.org/W6743802245","https://openalex.org/W6744838376","https://openalex.org/W6747473740","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6752736450","https://openalex.org/W6756687206","https://openalex.org/W6756848961","https://openalex.org/W6775522024","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3207061160","https://openalex.org/W3037785630","https://openalex.org/W1898758362","https://openalex.org/W2980523418","https://openalex.org/W2982783150","https://openalex.org/W3046387304","https://openalex.org/W587704066","https://openalex.org/W3011203923","https://openalex.org/W3131531515","https://openalex.org/W1971703870","https://openalex.org/W3009584224","https://openalex.org/W1580887022","https://openalex.org/W2168579783","https://openalex.org/W2771858866","https://openalex.org/W3110059731","https://openalex.org/W2795561664","https://openalex.org/W3049260422","https://openalex.org/W2354083731","https://openalex.org/W3207203964","https://openalex.org/W3202630042"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,94],"(RL)":[2],"has":[3,81],"achieved":[4],"some":[5],"impressive":[6],"recent":[7],"successes":[8,18],"in":[9,95,157,165,177],"various":[10],"computer":[11],"games":[12],"and":[13,75,129,160],"simulations.":[14],"Most":[15],"of":[16,25,40,59,168,181],"these":[17],"are":[19,173],"based":[20,142],"on":[21,86,120,161],"having":[22],"large":[23],"numbers":[24],"episodes":[26,180],"from":[27],"which":[28],"the":[29,38,57,99,121,130,133,162],"agent":[30],"can":[31,111],"learn.":[32],"In":[33,46,64,107],"typical":[34],"robotic":[35],"applications,":[36],"however,":[37],"number":[39,167],"feasible":[41],"attempts":[42],"is":[43,69,101,132,188],"very":[44],"limited.":[45],"this":[47,108],"paper":[48],"we":[49,110],"present":[50],"a":[51,60,87,113,158,166],"sample-efficient":[52],"RL":[53],"algorithm":[54,146],"applied":[55],"to":[56,82],"example":[58],"table":[61,65],"tennis":[62,66],"robot.":[63],"every":[67],"stroke":[68],"different,":[70],"with":[71],"varying":[72],"placement,":[73],"speed":[74],"spin.":[76],"An":[77,140],"accurate":[78],"return":[79],"therefore":[80],"be":[83],"found":[84],"depending":[85],"high-dimensional":[88],"continuous":[89],"state":[90,117,135],"space.":[91],"To":[92],"make":[93],"few":[96],"trials":[97],"possible":[98],"method":[100],"embedded":[102],"into":[103],"our":[104,186],"robot":[105,164],"system.":[106],"way":[109],"use":[112],"one-step":[114],"environment.":[115],"The":[116,183],"space":[118],"depends":[119],"ball":[122],"at":[123,138,190],"hitting":[124],"time":[125],"(position,":[126],"velocity,":[127],"spin)":[128],"action":[131],"racket":[134],"(orientation,":[136],"velocity)":[137],"hitting.":[139],"actor-critic":[141],"deterministic":[143],"policy":[144],"gradient":[145],"was":[147],"developed":[148],"for":[149],"accelerated":[150],"learning.":[151],"Our":[152],"approach":[153],"performs":[154],"competitively":[155],"both":[156],"simulation":[159],"real":[163],"challenging":[169],"scenarios.":[170],"Accurate":[171],"results":[172],"obtained":[174],"without":[175],"pre-training":[176],"under":[178],"$200$":[179],"training.":[182],"video":[184],"presenting":[185],"experiments":[187],"available":[189],"https://youtu.be/uRAtdoL6Wpw.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}