{"id":"https://openalex.org/W4312470006","doi":"https://doi.org/10.1109/lra.2022.3229266","title":"Learning to Throw With a Handful of Samples Using Decision Transformers","display_name":"Learning to Throw With a Handful of Samples Using Decision Transformers","publication_year":2022,"publication_date":"2022-12-14","ids":{"openalex":"https://openalex.org/W4312470006","doi":"https://doi.org/10.1109/lra.2022.3229266"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3229266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3229266","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5047713652","display_name":"Maxim Monastirsky","orcid":"https://orcid.org/0000-0001-6655-1823"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Maxim Monastirsky","raw_affiliation_strings":["School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0001-6655-1823","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030031036","display_name":"Osher Azulay","orcid":"https://orcid.org/0000-0002-7188-9201"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Osher Azulay","raw_affiliation_strings":["School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0002-7188-9201","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030565378","display_name":"Avishai Sintov","orcid":"https://orcid.org/0000-0002-3320-3897"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Avishai Sintov","raw_affiliation_strings":["School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel"],"raw_orcid":"https://orcid.org/0000-0002-3320-3897","affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Tel-Aviv University, Tel-Aviv, Israel","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047713652"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":1.8049,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87575427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"8","issue":"2","first_page":"576","last_page":"583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9980999827384949,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9868000149726868,"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/throwing","display_name":"Throwing","score":0.8126446604728699},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6132394671440125},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6091765761375427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5585047602653503},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46020740270614624},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4563619792461395},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45293572545051575},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4480038583278656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17748695611953735},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14964905381202698},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.08580049872398376}],"concepts":[{"id":"https://openalex.org/C207451115","wikidata":"https://www.wikidata.org/wiki/Q12898216","display_name":"Throwing","level":2,"score":0.8126446604728699},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6132394671440125},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6091765761375427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5585047602653503},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46020740270614624},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4563619792461395},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45293572545051575},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4480038583278656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17748695611953735},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14964905381202698},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.08580049872398376},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3229266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3229266","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G3722166068","display_name":null,"funder_award_id":"1565/20","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1481659984","https://openalex.org/W1530419089","https://openalex.org/W2017957151","https://openalex.org/W2047191624","https://openalex.org/W2111474706","https://openalex.org/W2342662072","https://openalex.org/W2592538810","https://openalex.org/W2767050701","https://openalex.org/W2807340089","https://openalex.org/W2843189636","https://openalex.org/W2896457183","https://openalex.org/W2904453761","https://openalex.org/W2962787969","https://openalex.org/W2963092423","https://openalex.org/W2963864421","https://openalex.org/W2980433389","https://openalex.org/W3022566517","https://openalex.org/W3088310808","https://openalex.org/W3092627351","https://openalex.org/W3094502228","https://openalex.org/W3101442004","https://openalex.org/W3120778962","https://openalex.org/W3129576130","https://openalex.org/W3132593015","https://openalex.org/W3138735759","https://openalex.org/W3169291081","https://openalex.org/W3214160581","https://openalex.org/W4283701713","https://openalex.org/W4287126489","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W4385245566","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6687534646","https://openalex.org/W6704571135","https://openalex.org/W6739901393","https://openalex.org/W6740801417","https://openalex.org/W6752216966","https://openalex.org/W6755207826","https://openalex.org/W6757469721","https://openalex.org/W6768810269","https://openalex.org/W6776438516","https://openalex.org/W6779576048","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6796289742","https://openalex.org/W6804244202","https://openalex.org/W6804532865","https://openalex.org/W6839526036"],"related_works":["https://openalex.org/W2757445715","https://openalex.org/W4239855920","https://openalex.org/W2371249440","https://openalex.org/W2365576545","https://openalex.org/W4226007727","https://openalex.org/W2059660105","https://openalex.org/W2327671128","https://openalex.org/W3029718387","https://openalex.org/W2386414876","https://openalex.org/W3036965803"],"abstract_inverted_index":{"Throwing":[0],"objects":[1,162],"by":[2,115],"a":[3,95,113,127],"robot":[4],"extends":[5],"its":[6],"reach":[7],"and":[8,89,111,178,198],"has":[9],"many":[10],"industrial":[11],"applications.":[12],"While":[13],"analytical":[14],"models":[15],"can":[16,31,176],"provide":[17,32],"efficient":[18],"performance,":[19],"they":[20,41],"require":[21,42],"accurate":[22,34,164,208],"estimation":[23],"of":[24,46,85,156,169],"system":[25],"parameters.":[26],"Reinforcement":[27],"Learning":[28],"(RL)":[29],"algorithms":[30],"an":[33,43,147,167,207],"throwing":[35],"policy":[36,97],"without":[37,133],"prior":[38,135],"knowledge.":[39],"However,":[40],"extensive":[44],"amount":[45],"real":[47,76,157],"world":[48],"samples":[49],"which":[50],"may":[51],"be":[52],"time":[53],"consuming":[54],"and,":[55],"most":[56,68],"importantly,":[57],"pose":[58],"danger.":[59],"Training":[60],"in":[61,71,201],"simulation,":[62,202],"on":[63,74,123,137,146,160],"the":[64,75,83,99,106,142,174,187],"other":[65],"hand,":[66],"would":[67],"likely":[69],"result":[70],"poor":[72],"performance":[73],"robot.":[77],"In":[78],"this":[79],"letter,":[80],"we":[81,104],"explore":[82],"use":[84],"Decision":[86],"Transformers":[87],"(DT)":[88],"their":[90],"ability":[91],"to":[92,102,139,181,186],"transfer":[93],"from":[94,126],"simulation-based":[96],"into":[98],"real-world.":[100],"Contrary":[101],"RL,":[103],"re-frame":[105],"problem":[107],"as":[108],"sequence":[109],"modelling":[110],"train":[112],"DT":[114,119,143,175],"supervised":[116],"learning.":[117],"The":[118],"is":[120,144],"trained":[121],"off-line":[122],"data":[124],"collected":[125],"far-from-reality":[128],"simulation":[129],"through":[130],"random":[131],"actions":[132],"any":[134],"knowledge":[136],"how":[138],"throw.":[140],"Then,":[141],"fine-tuned":[145],"handful":[148],"(":[149],"<inline-formula":[150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[152],"notation=\"LaTeX\">$\\sim":[153],"5$</tex-math></inline-formula>":[154],")":[155],"throws.":[158],"Results":[159],"various":[161],"show":[163,192],"throws":[165],"reaching":[166],"error":[168],"approximately":[170],"4":[171],"cm.":[172],"Also,":[173],"extrapolate":[177],"accurately":[179],"throw":[180,196],"goals":[182],"that":[183,193],"are":[184,203],"out-of-distribution":[185],"training":[188,206],"data.":[189],"We":[190],"additionally":[191],"few":[194],"expert":[195],"samples,":[197],"no":[199],"pre-training":[200],"sufficient":[204],"for":[205],"policy.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}