{"id":"https://openalex.org/W4401416214","doi":"https://doi.org/10.1109/icra57147.2024.10610040","title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","display_name":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416214","doi":"https://doi.org/10.1109/icra57147.2024.10610040"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5037464692","display_name":"Jianlan Luo","orcid":"https://orcid.org/0009-0008-8029-7794"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jianlan Luo","raw_affiliation_strings":["University of California,Department of EECS,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Department of EECS,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090943765","display_name":"Zheyuan Hu","orcid":"https://orcid.org/0000-0002-0116-9874"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheyuan Hu","raw_affiliation_strings":["University of California,Department of EECS,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Department of EECS,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076432186","display_name":"Charles Xu","orcid":"https://orcid.org/0009-0007-9126-3680"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Xu","raw_affiliation_strings":["University of California,Department of EECS,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Department of EECS,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102674055","display_name":"You Liang Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"You Liang Tan","raw_affiliation_strings":["University of California,Department of EECS,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Department of EECS,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049190607","display_name":"Jacob Berg","orcid":"https://orcid.org/0000-0003-2126-6476"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Berg","raw_affiliation_strings":["University of Washington,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"University of Washington,Department of Computer Science","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033189369","display_name":"Archit Sharma","orcid":"https://orcid.org/0000-0001-9487-1576"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Archit Sharma","raw_affiliation_strings":["Stanford University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[{"id":"https://openalex.org/I4210105824","display_name":"Intrinsic LifeSciences (United States)","ror":"https://ror.org/01maah330","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105824"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Intrinsic Innovation LLC"],"affiliations":[{"raw_affiliation_string":"Intrinsic Innovation LLC","institution_ids":["https://openalex.org/I4210105824"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Stanford University,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Computer Science","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017906439","display_name":"Abhishek Gupta","orcid":"https://orcid.org/0000-0003-1117-325X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek Gupta","raw_affiliation_strings":["University of Washington,Department of Computer Science"],"affiliations":[{"raw_affiliation_string":"University of Washington,Department of Computer Science","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["University of California,Department of EECS,Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California,Department of EECS,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5037464692"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":9.2307,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.98542188,"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":"16961","last_page":"16969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9979000091552734,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9890999794006348,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.858900785446167},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7972548007965088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7186349034309387},{"id":"https://openalex.org/keywords/software-suite","display_name":"Software suite","score":0.6017777919769287},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5987530946731567},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5733287334442139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4289144277572632},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16780835390090942}],"concepts":[{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.858900785446167},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7972548007965088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186349034309387},{"id":"https://openalex.org/C2778736646","wikidata":"https://www.wikidata.org/wiki/Q1143070","display_name":"Software suite","level":3,"score":0.6017777919769287},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5987530946731567},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5733287334442139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4289144277572632},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16780835390090942},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W2097797606","https://openalex.org/W2127412976","https://openalex.org/W2155007355","https://openalex.org/W2194775991","https://openalex.org/W2221677593","https://openalex.org/W2806130867","https://openalex.org/W2909718913","https://openalex.org/W2962736495","https://openalex.org/W2963411833","https://openalex.org/W2967355195","https://openalex.org/W2968268581","https://openalex.org/W2968340082","https://openalex.org/W3007769740","https://openalex.org/W3037785630","https://openalex.org/W3109467707","https://openalex.org/W3130717831","https://openalex.org/W3159735414","https://openalex.org/W3174364619","https://openalex.org/W3206200647","https://openalex.org/W3206827162","https://openalex.org/W3207061160","https://openalex.org/W4292103799","https://openalex.org/W4293864724","https://openalex.org/W4298857966","https://openalex.org/W4319453704","https://openalex.org/W4320013936","https://openalex.org/W4324299512","https://openalex.org/W4367016688","https://openalex.org/W4385430474","https://openalex.org/W4385430550","https://openalex.org/W4385430633","https://openalex.org/W4386554805","https://openalex.org/W4388964486","https://openalex.org/W6637967152","https://openalex.org/W6682849425","https://openalex.org/W6683195989","https://openalex.org/W6735571901","https://openalex.org/W6737327832","https://openalex.org/W6746595151","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6752338937","https://openalex.org/W6757222794","https://openalex.org/W6765121789","https://openalex.org/W6767997047","https://openalex.org/W6768397756","https://openalex.org/W6769596995","https://openalex.org/W6771179988","https://openalex.org/W6780559895","https://openalex.org/W6787971688","https://openalex.org/W6793853427","https://openalex.org/W6795923368","https://openalex.org/W6804112224","https://openalex.org/W6839204832","https://openalex.org/W6839390831","https://openalex.org/W6840645976","https://openalex.org/W6841950565","https://openalex.org/W6845793730","https://openalex.org/W6846686744","https://openalex.org/W6849433528","https://openalex.org/W6850495229","https://openalex.org/W6851152319","https://openalex.org/W6853053110","https://openalex.org/W6856118858","https://openalex.org/W6858612488"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W1516095885","https://openalex.org/W2158573927","https://openalex.org/W2108921801","https://openalex.org/W4206079007","https://openalex.org/W1981336497","https://openalex.org/W2398058485","https://openalex.org/W254965819","https://openalex.org/W4205365843","https://openalex.org/W3156231268"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"significant":[3,81],"progress":[4],"has":[5],"been":[6],"made":[7],"in":[8,24,210,255],"the":[9,25,54,73,84,93,101,133,158,211,248],"field":[10],"of":[11,58,75,87,96,104,146,196],"robotic":[12,42,88,97,256],"reinforcement":[13],"learning":[14],"(RL),":[15],"enabling":[16],"methods":[17,127],"that":[18,53,79,172],"handle":[19],"complex":[20],"image":[21],"observations,":[22],"train":[23],"real":[26],"world,":[27],"and":[28,35,131,143,164,188,226,230,238,261],"incorporate":[29],"auxiliary":[30],"data,":[31],"such":[32,105],"as":[33,64,72,90,92,154],"demonstrations":[34],"prior":[36],"experience.":[37],"However,":[38],"despite":[39],"these":[40,59,235],"advances,":[41],"RL":[43,98,123],"remains":[44],"hard":[45],"to":[46,83,193,251],"use.":[47],"It":[48],"is":[49,100],"acknowledged":[50],"among":[51],"practitioners":[52],"particular":[55],"implementation":[56,174,242],"details":[57],"algorithms":[60],"are":[61],"often":[62],"just":[63],"important":[65],"(if":[66],"not":[67],"more":[68],"so)":[69],"for":[70,128,138,157,182,207,247],"performance":[71],"choice":[74],"algorithm.":[76],"We":[77,150,233],"posit":[78],"a":[80,113,118,135,139,144,155,245],"challenge":[82],"widespread":[85],"adoption":[86],"RL,":[89],"well":[91],"further":[94,253],"development":[95],"methods,":[99],"comparative":[102],"inaccessibility":[103],"methods.":[106],"To":[107],"address":[108],"this":[109,152],"challenge,":[110],"we":[111,170],"developed":[112],"carefully":[114],"implemented":[115],"library":[116,153],"containing":[117],"sample":[119],"efficient":[120,178],"off-policy":[121],"deep":[122],"method,":[124],"together":[125],"with":[126],"computing":[129],"rewards":[130],"resetting":[132],"environment,":[134],"high-quality":[136,240],"controller":[137],"widely":[140],"adopted":[141],"robot,":[142],"number":[145],"challenging":[147],"example":[148],"tasks.":[149],"provide":[151,244],"resource":[156],"community,":[159],"describe":[160],"its":[161],"design":[162],"choices,":[163],"present":[165],"experimental":[166],"results.":[167],"Perhaps":[168],"surprisingly,":[169],"find":[171],"our":[173,239],"can":[175,263],"achieve":[176,215],"very":[177],"learning,":[179],"acquiring":[180],"policies":[181,214],"PCB":[183],"board":[184],"assembly,":[185],"cable":[186],"routing,":[187],"object":[189],"relocation":[190],"between":[191],"25":[192],"50":[194],"minutes":[195],"training":[197],"per":[198],"policy":[199],"on":[200],"average,":[201],"improving":[202],"over":[203],"state-of-the-art":[204],"results":[205,237],"reported":[206],"similar":[208],"tasks":[209],"literature.":[212],"These":[213],"perfect":[216],"or":[217],"near-perfect":[218],"success":[219],"rates,":[220],"extreme":[221],"robustness":[222],"even":[223],"under":[224],"perturbations,":[225],"exhibit":[227],"emergent":[228],"recovery":[229],"correction":[231],"behaviors.":[232],"hope":[234],"promising":[236],"open-source":[241],"will":[243],"tool":[246],"robotics":[249],"community":[250],"facilitate":[252],"developments":[254],"RL.":[257],"Our":[258],"code,":[259],"documentation,":[260],"videos":[262],"be":[264],"found":[265],"at":[266],"https://serl-robot.github.io/":[267]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}