{"id":"https://openalex.org/W4401416949","doi":"https://doi.org/10.1109/icra57147.2024.10611494","title":"Experience Consistency Distillation Continual Reinforcement Learning for Robotic Manipulation Tasks","display_name":"Experience Consistency Distillation Continual Reinforcement Learning for Robotic Manipulation Tasks","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416949","doi":"https://doi.org/10.1109/icra57147.2024.10611494"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611494","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/A5071320121","display_name":"Chao Zhao","orcid":"https://orcid.org/0000-0003-1116-0790"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Zhao","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003488506","display_name":"Jie Xu","orcid":"https://orcid.org/0000-0002-2039-7055"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Xu","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101517784","display_name":"Ru Peng","orcid":"https://orcid.org/0000-0002-2122-5263"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru Peng","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004275338","display_name":"Xingyu Chen","orcid":"https://orcid.org/0000-0002-5226-963X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Chen","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034840700","display_name":"Kuizhi Mei","orcid":"https://orcid.org/0000-0002-8119-3726"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuizhi Mei","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006277484","display_name":"Xuguang Lan","orcid":"https://orcid.org/0000-0002-3422-944X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,Institute of Artificial Intelligence and Robotics,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5071320121"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.7274,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75345846,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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":0.9958000183105469,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9747999906539917,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9527000188827515,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8018150925636292},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7529603242874146},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7507419586181641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6959550976753235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5138871669769287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35628217458724976},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.056180983781814575}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8018150925636292},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7529603242874146},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7507419586181641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959550976753235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5138871669769287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35628217458724976},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.056180983781814575},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611494","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611494","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2560647685","https://openalex.org/W2736601468","https://openalex.org/W2768629321","https://openalex.org/W2904246096","https://openalex.org/W2930863966","https://openalex.org/W2963559848","https://openalex.org/W2964189064","https://openalex.org/W2996514457","https://openalex.org/W3032949543","https://openalex.org/W3094314265","https://openalex.org/W3127177108","https://openalex.org/W3142096533","https://openalex.org/W3158253560","https://openalex.org/W3165631200","https://openalex.org/W3168149265","https://openalex.org/W3181648466","https://openalex.org/W3182820356","https://openalex.org/W3182849481","https://openalex.org/W3198317271","https://openalex.org/W3198953397","https://openalex.org/W3211352205","https://openalex.org/W3216968833","https://openalex.org/W4281768461","https://openalex.org/W4283590445","https://openalex.org/W4287065492","https://openalex.org/W4287177585","https://openalex.org/W4301206121","https://openalex.org/W4312412605","https://openalex.org/W4319988532","https://openalex.org/W4385488764","https://openalex.org/W6631190155","https://openalex.org/W6738602802","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6756054015","https://openalex.org/W6757384668","https://openalex.org/W6757592117","https://openalex.org/W6765779288","https://openalex.org/W6769596995","https://openalex.org/W6778804409","https://openalex.org/W6779630500","https://openalex.org/W6780397927","https://openalex.org/W6784399590","https://openalex.org/W6788757688","https://openalex.org/W6797362500","https://openalex.org/W6799502010","https://openalex.org/W6810040637","https://openalex.org/W6839533060","https://openalex.org/W6849896277"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Continual":[0],"reinforcement":[1,34,88,178],"learning,":[2],"which":[3],"aims":[4],"to":[5,16,24,50,90,106,144,205],"help":[6],"robots":[7],"acquire":[8],"skills":[9,29],"without":[10],"catastrophic":[11],"forgetting,":[12],"obviating":[13],"the":[14,66,92,96,99,149,156,176],"need":[15],"re-learn":[17],"all":[18],"tasks":[19,49,71,103],"from":[20,47],"scratch.":[21],"In":[22,142],"order":[23,143],"enable":[25],"lifelong":[26],"acquisition":[27],"of":[28,69,95,101],"in":[30,175],"robots,":[31],"replay-based":[32,59],"continual":[33,87,177],"learning":[35,54,89,179],"has":[36],"emerged":[37],"as":[38,138],"a":[39,132,139,186],"promising":[40],"research":[41],"direction.":[42],"These":[43],"techniques":[44],"replay":[45],"data":[46,93,112,123,158],"previous":[48],"mitigate":[51],"forgetting":[52],"when":[53],"new":[55],"skills.":[56],"However,":[57],"existing":[58],"methods":[60],"store":[61],"poor":[62],"representative":[63],"experience,":[64],"and":[65,117,126,159,182,199],"experience":[67,81,100,146],"utilization":[68,147],"old":[70,102],"is":[72,151,173],"inefficient.":[73],"To":[74,120],"address":[75],"these":[76],"issues,":[77],"we":[78,129],"propose":[79],"an":[80],"consistency":[82],"distillation":[83,165],"method":[84,172,195],"for":[85],"robot":[86,188],"improve":[91,145],"efficiency":[94],"experience.":[97],"Specifically,":[98],"are":[104],"distilled":[105,157],"obtain":[107],"Markov":[108],"Decision":[109],"Process":[110],"(MDP)":[111],"with":[113,163,185],"high":[114],"compression":[115],"ratio":[116],"information":[118],"content.":[119],"ensure":[121],"consistent":[122],"distributions":[124],"before":[125],"after":[127],"distillation,":[128],"further":[130],"utilize":[131],"Fr\u00e9chet":[133],"Inception":[134],"Distance":[135],"(FID)":[136],"loss":[137],"regularization":[140],"constraint.":[141],"efficiency,":[148],"policy":[150,164],"then":[152],"trained":[153],"using":[154],"both":[155],"current":[160],"task":[161],"data,":[162],"performed":[166],"based":[167],"on":[168],"uncertainty":[169],"metrics.":[170],"Our":[171],"validated":[174],"simulation":[180],"platform":[181],"real":[183],"scene":[184],"UR5e":[187],"arm.":[189],"Experimental":[190],"results":[191],"indicate":[192],"that":[193],"our":[194],"achieves":[196],"higher":[197],"success":[198],"lower":[200],"buffer":[201],"size":[202],"requirement":[203],"compared":[204],"other":[206],"methods.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}