{"id":"https://openalex.org/W4404738510","doi":"https://doi.org/10.1146/annurev-control-030323-022510","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","display_name":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4404738510","doi":"https://doi.org/10.1146/annurev-control-030323-022510"},"language":"en","primary_location":{"id":"doi:10.1146/annurev-control-030323-022510","is_oa":true,"landing_page_url":"https://doi.org/10.1146/annurev-control-030323-022510","pdf_url":null,"source":{"id":"https://openalex.org/S4210191328","display_name":"Annual Review of Control Robotics and Autonomous Systems","issn_l":"2573-5144","issn":["2573-5144"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320373","host_organization_name":"Annual Reviews","host_organization_lineage":["https://openalex.org/P4310320373"],"host_organization_lineage_names":["Annual Reviews"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Review of Control, Robotics, and Autonomous Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1146/annurev-control-030323-022510","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101867083","display_name":"Chen Tang","orcid":"https://orcid.org/0000-0002-7536-9983"},"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":"Chen Tang","raw_affiliation_strings":["1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003639695","display_name":"Ben Abbatematteo","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":"Ben Abbatematteo","raw_affiliation_strings":["1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089998046","display_name":"Jiaheng Hu","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":"Jiaheng Hu","raw_affiliation_strings":["1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016704715","display_name":"Rohan Chandra","orcid":"https://orcid.org/0000-0003-4843-6375"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohan Chandra","raw_affiliation_strings":["2Department of Computer Science, The University of Virginia, Charlottesville, Virginia, USA; email: rohanchandra@virginia.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"2Department of Computer Science, The University of Virginia, Charlottesville, Virginia, USA; email: rohanchandra@virginia.edu","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065655761","display_name":"Roberto Mart\u00edn-Mart\u00edn","orcid":"https://orcid.org/0000-0002-9586-2759"},"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":"Roberto Mart\u00edn-Mart\u00edn","raw_affiliation_strings":["1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu","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":["1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu","3Sony AI, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"1Department of Computer Science, The University of Texas at Austin, Austin, Texas, USA; email: chen.tang@utexas.edu, abba@cs.utexas.edu, jiahengh@utexas.edu, robertomm@cs.utexas.edu, pstone@utexas.edu","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"3Sony AI, New York, NY, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":29.5621,"has_fulltext":false,"cited_by_count":122,"citation_normalized_percentile":{"value":0.99788577,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"153","last_page":"188"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.948199987411499,"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":0.948199987411499,"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/robotics","display_name":"Robotics","score":0.7445997595787048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6759889721870422},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6702139973640442},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43949806690216064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3657570481300354},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26445722579956055},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2199067771434784},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07387986779212952}],"concepts":[{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.7445997595787048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6759889721870422},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6702139973640442},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43949806690216064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3657570481300354},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26445722579956055},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2199067771434784},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07387986779212952}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1146/annurev-control-030323-022510","is_oa":true,"landing_page_url":"https://doi.org/10.1146/annurev-control-030323-022510","pdf_url":null,"source":{"id":"https://openalex.org/S4210191328","display_name":"Annual Review of Control Robotics and Autonomous Systems","issn_l":"2573-5144","issn":["2573-5144"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320373","host_organization_name":"Annual Reviews","host_organization_lineage":["https://openalex.org/P4310320373"],"host_organization_lineage_names":["Annual Reviews"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Review of Control, Robotics, and Autonomous Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1146/annurev-control-030323-022510","is_oa":true,"landing_page_url":"https://doi.org/10.1146/annurev-control-030323-022510","pdf_url":null,"source":{"id":"https://openalex.org/S4210191328","display_name":"Annual Review of Control Robotics and Autonomous Systems","issn_l":"2573-5144","issn":["2573-5144"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320373","host_organization_name":"Annual Reviews","host_organization_lineage":["https://openalex.org/P4310320373"],"host_organization_lineage_names":["Annual Reviews"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Review of Control, Robotics, and Autonomous Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":195,"referenced_works":["https://openalex.org/W165566157","https://openalex.org/W192919555","https://openalex.org/W1977655452","https://openalex.org/W2130105540","https://openalex.org/W2135929901","https://openalex.org/W2139053308","https://openalex.org/W2155007355","https://openalex.org/W2157055752","https://openalex.org/W2169209873","https://openalex.org/W2212573275","https://openalex.org/W2522340145","https://openalex.org/W2524264252","https://openalex.org/W2565902248","https://openalex.org/W2592873849","https://openalex.org/W2604216058","https://openalex.org/W2732319713","https://openalex.org/W2733312032","https://openalex.org/W2736601468","https://openalex.org/W2738778707","https://openalex.org/W2741122588","https://openalex.org/W2759463506","https://openalex.org/W2766614170","https://openalex.org/W2770387316","https://openalex.org/W2786110872","https://openalex.org/W2788741142","https://openalex.org/W2788781499","https://openalex.org/W2789839425","https://openalex.org/W2794537597","https://openalex.org/W2797862905","https://openalex.org/W2798273187","https://openalex.org/W2800978878","https://openalex.org/W2808844346","https://openalex.org/W2823112946","https://openalex.org/W2892258706","https://openalex.org/W2897345632","https://openalex.org/W2899201819","https://openalex.org/W2902125520","https://openalex.org/W2904746163","https://openalex.org/W2905464683","https://openalex.org/W2910474428","https://openalex.org/W2911087563","https://openalex.org/W2912063360","https://openalex.org/W2913754617","https://openalex.org/W2921077764","https://openalex.org/W2929174622","https://openalex.org/W2929928372","https://openalex.org/W2949275450","https://openalex.org/W2955035422","https://openalex.org/W2968800739","https://openalex.org/W2969281871","https://openalex.org/W2975909688","https://openalex.org/W2976965990","https://openalex.org/W2981759303","https://openalex.org/W2982292643","https://openalex.org/W2989847975","https://openalex.org/W2990747716","https://openalex.org/W2995058766","https://openalex.org/W3001975179","https://openalex.org/W3003533476","https://openalex.org/W3005451807","https://openalex.org/W3015395340","https://openalex.org/W3020825567","https://openalex.org/W3031798691","https://openalex.org/W3032919895","https://openalex.org/W3034786558","https://openalex.org/W3037785630","https://openalex.org/W3038582969","https://openalex.org/W3040041096","https://openalex.org/W3049043369","https://openalex.org/W3093922502","https://openalex.org/W3095999515","https://openalex.org/W3096243380","https://openalex.org/W3100366369","https://openalex.org/W3111294788","https://openalex.org/W3112664346","https://openalex.org/W3121342653","https://openalex.org/W3123348991","https://openalex.org/W3126321819","https://openalex.org/W3127756416","https://openalex.org/W3137030294","https://openalex.org/W3140042148","https://openalex.org/W3148290239","https://openalex.org/W3156232699","https://openalex.org/W3161634385","https://openalex.org/W3162157701","https://openalex.org/W3173701235","https://openalex.org/W3175254947","https://openalex.org/W3178099496","https://openalex.org/W3195968524","https://openalex.org/W3197318324","https://openalex.org/W3200650887","https://openalex.org/W3201555865","https://openalex.org/W3202883604","https://openalex.org/W3204657926","https://openalex.org/W3206530605","https://openalex.org/W3206827162","https://openalex.org/W3207033168","https://openalex.org/W3209193306","https://openalex.org/W3210150378","https://openalex.org/W3216930691","https://openalex.org/W4205430897","https://openalex.org/W4210491718","https://openalex.org/W4210870706","https://openalex.org/W4212766024","https://openalex.org/W4214634122","https://openalex.org/W4220817121","https://openalex.org/W4220840735","https://openalex.org/W4221138321","https://openalex.org/W4221139039","https://openalex.org/W4221139068","https://openalex.org/W4223534396","https://openalex.org/W4282007574","https://openalex.org/W4283721947","https://openalex.org/W4285077530","https://openalex.org/W4285273130","https://openalex.org/W4287391859","https://openalex.org/W4288043501","https://openalex.org/W4295680071","https://openalex.org/W4296563123","https://openalex.org/W4297411839","https://openalex.org/W4297947592","https://openalex.org/W4302010007","https://openalex.org/W4304732191","https://openalex.org/W4306893292","https://openalex.org/W4307415550","https://openalex.org/W4307415921","https://openalex.org/W4307535988","https://openalex.org/W4308242512","https://openalex.org/W4308619662","https://openalex.org/W4309137642","https://openalex.org/W4310886200","https://openalex.org/W4311992093","https://openalex.org/W4312610897","https://openalex.org/W4312908419","https://openalex.org/W4317987839","https://openalex.org/W4318241718","https://openalex.org/W4318902851","https://openalex.org/W4323572066","https://openalex.org/W4323651349","https://openalex.org/W4323927407","https://openalex.org/W4353007652","https://openalex.org/W4361866148","https://openalex.org/W4362599025","https://openalex.org/W4362599058","https://openalex.org/W4366566350","https://openalex.org/W4375957488","https://openalex.org/W4375959541","https://openalex.org/W4376864769","https://openalex.org/W4377864772","https://openalex.org/W4378464660","https://openalex.org/W4378760022","https://openalex.org/W4380551489","https://openalex.org/W4381247816","https://openalex.org/W4381247851","https://openalex.org/W4381252744","https://openalex.org/W4381832832","https://openalex.org/W4382362889","https://openalex.org/W4382365724","https://openalex.org/W4385430550","https://openalex.org/W4386090379","https://openalex.org/W4386285856","https://openalex.org/W4386718967","https://openalex.org/W4386874604","https://openalex.org/W4386942526","https://openalex.org/W4387191527","https://openalex.org/W4387433367","https://openalex.org/W4387964172","https://openalex.org/W4388585636","https://openalex.org/W4388901983","https://openalex.org/W4389649713","https://openalex.org/W4389768224","https://openalex.org/W4389820524","https://openalex.org/W4390938336","https://openalex.org/W4390963150","https://openalex.org/W4391272997","https://openalex.org/W4391421221","https://openalex.org/W4391462671","https://openalex.org/W4392341560","https://openalex.org/W4392425996","https://openalex.org/W4392490311","https://openalex.org/W4392576560","https://openalex.org/W4392763392","https://openalex.org/W4393023555","https://openalex.org/W4393213899","https://openalex.org/W4393972737","https://openalex.org/W4394674699","https://openalex.org/W4395116617","https://openalex.org/W4396542455","https://openalex.org/W4396786046","https://openalex.org/W4396822572","https://openalex.org/W4396914187","https://openalex.org/W4399414059","https://openalex.org/W4399794218","https://openalex.org/W4401413922","https://openalex.org/W4402467023"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4233452137","https://openalex.org/W4254857216","https://openalex.org/W4231626925","https://openalex.org/W2962829499","https://openalex.org/W2767518918","https://openalex.org/W2131444840","https://openalex.org/W2414929284","https://openalex.org/W192849109"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL),":[2],"particularly":[3],"its":[4,27],"combination":[5],"with":[6,56,70,80],"deep":[7,13],"neural":[8],"networks,":[9],"referred":[10],"to":[11,91,141,157,170],"as":[12],"RL":[14,131,162],"(DRL),":[15],"has":[16],"shown":[17],"tremendous":[18],"promise":[19],"across":[20],"a":[21,63,71],"wide":[22],"range":[23],"of":[24,33,46,54,66,108,111],"applications,":[25],"suggesting":[26],"potential":[28],"for":[29,43,68,120,126,135,160],"enabling":[30],"the":[31,44,50,57,76,93,109,124],"development":[32,149],"sophisticated":[34],"robotic":[35,86,175],"behaviors.":[36],"Robotics":[37],"problems,":[38],"however,":[39],"pose":[40],"fundamental":[41],"difficulties":[42],"application":[45],"RL,":[47],"stemming":[48],"from":[49],"complexity":[51],"and":[52,103,128,137,147,150,164],"cost":[53],"interacting":[55],"physical":[58],"world.":[59],"This":[60,153],"article":[61],"provides":[62],"modern":[64],"survey":[65,154],"DRL":[67,81,112],"robotics,":[69],"particular":[72],"focus":[73],"on":[74],"evaluating":[75],"real-world":[77,130,174],"successes":[78],"achieved":[79],"in":[82,113],"realizing":[83],"several":[84,117],"key":[85,94],"competencies.":[87],"Our":[88],"analysis":[89],"aims":[90],"identify":[92],"factors":[95],"underlying":[96],"those":[97],"exciting":[98],"successes,":[99],"reveal":[100],"underexplored":[101],"areas,":[102],"provide":[104],"an":[105],"overall":[106],"characterization":[107],"status":[110],"robotics.":[114],"We":[115],"highlight":[116],"important":[118],"avenues":[119],"future":[121],"work,":[122],"emphasizing":[123],"need":[125],"stable":[127],"sample-efficient":[129],"paradigms;":[132],"holistic":[133],"approaches":[134],"discovering":[136],"integrating":[138],"various":[139],"competencies":[140],"tackle":[142],"complex":[143],"long-horizon,":[144],"open-world":[145],"tasks;":[146],"principled":[148],"evaluation":[151],"procedures.":[152],"is":[155],"designed":[156],"offer":[158],"insights":[159],"both":[161],"practitioners":[163],"roboticists":[165],"toward":[166],"harnessing":[167],"RL's":[168],"power":[169],"create":[171],"generally":[172],"capable":[173],"systems.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":64},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}