{"id":"https://openalex.org/W4401413712","doi":"https://doi.org/10.1109/icra57147.2024.10610485","title":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","display_name":"Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401413712","doi":"https://doi.org/10.1109/icra57147.2024.10610485"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610485","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/A5057441223","display_name":"Laura Smith","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":"Laura Smith","raw_affiliation_strings":["Berkeley AI Research, UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley AI Research, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001507642","display_name":"Yun-Hao Cao","orcid":"https://orcid.org/0000-0002-6229-8469"},"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":"Yunhao Cao","raw_affiliation_strings":["Berkeley AI Research, UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley AI Research, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"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":["Berkeley AI Research, UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Berkeley AI Research, UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":2.5709,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.90832512,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10829","last_page":"10836"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.994700014591217,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9930999875068665,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6311172842979431},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43290746212005615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3979004919528961}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6311172842979431},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43290746212005615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3979004919528961}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610485","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W569478347","https://openalex.org/W1945123189","https://openalex.org/W2061983716","https://openalex.org/W2065238107","https://openalex.org/W2095705004","https://openalex.org/W2109008048","https://openalex.org/W2139053308","https://openalex.org/W2528489519","https://openalex.org/W2562736583","https://openalex.org/W2593412525","https://openalex.org/W2793991136","https://openalex.org/W2894779868","https://openalex.org/W2909553221","https://openalex.org/W2911087563","https://openalex.org/W2962736495","https://openalex.org/W2963082139","https://openalex.org/W2963184939","https://openalex.org/W2967998934","https://openalex.org/W2968213087","https://openalex.org/W3003647188","https://openalex.org/W3007553593","https://openalex.org/W3020712699","https://openalex.org/W3039737909","https://openalex.org/W3093922502","https://openalex.org/W3104876774","https://openalex.org/W3124816456","https://openalex.org/W3125087981","https://openalex.org/W3126321819","https://openalex.org/W3170422092","https://openalex.org/W3172115140","https://openalex.org/W3172321357","https://openalex.org/W3175254947","https://openalex.org/W3204665606","https://openalex.org/W3213886952","https://openalex.org/W4221155471","https://openalex.org/W4240896231","https://openalex.org/W4250058668","https://openalex.org/W4252189904","https://openalex.org/W4283787029","https://openalex.org/W4286963241","https://openalex.org/W4287209565","https://openalex.org/W4288319859","https://openalex.org/W4366736145","https://openalex.org/W4383109371","https://openalex.org/W4385430486","https://openalex.org/W4385430550","https://openalex.org/W4394674699","https://openalex.org/W6601848611","https://openalex.org/W6674330103","https://openalex.org/W6753243525","https://openalex.org/W6754162236","https://openalex.org/W6755667589","https://openalex.org/W6756192075","https://openalex.org/W6765121789","https://openalex.org/W6768397756","https://openalex.org/W6771217966","https://openalex.org/W6778428183","https://openalex.org/W6787186977","https://openalex.org/W6801064428","https://openalex.org/W6802202268","https://openalex.org/W6802654813","https://openalex.org/W6838667504"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2],"can":[3],"enable":[4],"robots":[5],"to":[6,67,70,81,114,121],"autonomously":[7],"acquire":[8],"complex":[9],"behaviors":[10],"such":[11],"as":[12],"legged":[13],"locomotion.":[14],"However,":[15],"RL":[16],"in":[17,73,90,100,116],"the":[18,46,74],"real":[19,75],"world":[20,76],"is":[21,104],"complicated":[22],"by":[23],"constraints":[24],"on":[25],"efficiency,":[26],"safety,":[27],"and":[28,58,79,112,119],"overall":[29],"training":[30,85,96],"stability,":[31],"which":[32],"limits":[33],"its":[34],"practical":[35],"applicability.":[36],"We":[37,92],"present":[38],"APRL,":[39],"a":[40,52,64,101],"policy":[41,102],"regularization":[42],"framework":[43],"that":[44,94,103],"modulates":[45],"robot\u2019s":[47],"exploration":[48],"throughout":[49],"training,":[50],"striking":[51],"balance":[53],"between":[54],"flexible":[55],"improvement":[56],"potential":[57],"focused,":[59],"efficient":[60],"exploration.":[61],"APRL":[62,98],"enables":[63],"quadrupedal":[65],"robot":[66],"efficiently":[68],"learn":[69],"walk":[71],"entirely":[72],"within":[77],"minutes":[78],"continue":[80],"improve":[82],"with":[83,97],"more":[84,106],"where":[86],"prior":[87],"work":[88],"saturates":[89],"performance.":[91],"demonstrate":[93],"continued":[95],"results":[99,124],"substantially":[105],"capable":[107],"of":[108],"navigating":[109],"challenging":[110],"situations":[111],"adapts":[113],"changes":[115],"dynamics.":[117],"Videos":[118],"code":[120],"reproduce":[122],"our":[123],"are":[125],"available":[126],"at:":[127],"https://sites.google.com/berkeley.edu/aprl":[128]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}