{"id":"https://openalex.org/W4396591355","doi":"https://doi.org/10.1017/s0263574724000389","title":"Learning vision-based robotic manipulation tasks sequentially in offline reinforcement learning settings","display_name":"Learning vision-based robotic manipulation tasks sequentially in offline reinforcement learning settings","publication_year":2024,"publication_date":"2024-05-02","ids":{"openalex":"https://openalex.org/W4396591355","doi":"https://doi.org/10.1017/s0263574724000389"},"language":"en","primary_location":{"id":"doi:10.1017/s0263574724000389","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574724000389","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","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/A5084833732","display_name":"Sudhir Pratap Yadav","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sudhir Pratap Yadav","raw_affiliation_strings":["iHub Drishti Foundation, Jodhpur, India, iHub Drishti Foundation"],"affiliations":[{"raw_affiliation_string":"iHub Drishti Foundation, Jodhpur, India, iHub Drishti Foundation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101754497","display_name":"Rajendra Nagar","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajendra Nagar","raw_affiliation_strings":["Department of Electrical Engineering, IIT Jodhpur, Jodhpur, India, IIT Jodhpur"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, IIT Jodhpur, Jodhpur, India, IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014630904","display_name":"Suril V. Shah","orcid":"https://orcid.org/0000-0002-6979-916X"},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suril V. Shah","raw_affiliation_strings":["Department of Mechanical Engineering, IIT Jodhpur, Jodhpur, India, IIT Jodhpur"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, IIT Jodhpur, Jodhpur, India, IIT Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084833732"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8112,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86600018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"42","issue":"6","first_page":"1715","last_page":"1730"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9968000054359436,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8132763504981995},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.7988914251327515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7865450382232666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7381154894828796},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6907023191452026},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5302680730819702},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5173436999320984},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.452285498380661},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45059216022491455},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.44539690017700195},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07630625367164612}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8132763504981995},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7988914251327515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865450382232666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7381154894828796},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6907023191452026},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5302680730819702},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5173436999320984},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.452285498380661},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45059216022491455},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.44539690017700195},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07630625367164612},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s0263574724000389","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s0263574724000389","pdf_url":null,"source":{"id":"https://openalex.org/S92163612","display_name":"Robotica","issn_l":"0263-5747","issn":["0263-5747","1469-8668"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotica","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1757796397","https://openalex.org/W2060277733","https://openalex.org/W2113839990","https://openalex.org/W2155968351","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2612690371","https://openalex.org/W2737770521","https://openalex.org/W2746553466","https://openalex.org/W2753818635","https://openalex.org/W2781726626","https://openalex.org/W2949268663","https://openalex.org/W2962871243","https://openalex.org/W2963403593","https://openalex.org/W2964262254","https://openalex.org/W2974295111","https://openalex.org/W3033324992","https://openalex.org/W3036642894","https://openalex.org/W3097907450","https://openalex.org/W3106539628","https://openalex.org/W3128507558","https://openalex.org/W3130717831","https://openalex.org/W3133805463","https://openalex.org/W3165631200","https://openalex.org/W3168941183","https://openalex.org/W3197400104","https://openalex.org/W3201555865","https://openalex.org/W3205429789","https://openalex.org/W3206200647","https://openalex.org/W3206507930","https://openalex.org/W3210150378","https://openalex.org/W4229007060","https://openalex.org/W4287177585","https://openalex.org/W4290098915","https://openalex.org/W4294936113","https://openalex.org/W6741130107","https://openalex.org/W6771876938","https://openalex.org/W6779265984","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2081982437","https://openalex.org/W4394857231","https://openalex.org/W2145559838","https://openalex.org/W2027050655","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W3028244590","https://openalex.org/W4254349500"],"abstract_inverted_index":{"Abstract":[0],"With":[1],"the":[2,20,91,102,115,136,163,171,174,180,193,202,216],"rise":[3],"of":[4,23,93,104,117,138,145,165,173,176,182,195,230],"deep":[5,24,95],"reinforcement":[6],"learning":[7,25,83,125,188],"(RL)":[8],"methods,":[9],"many":[10,47],"complex":[11],"robotic":[12,57,127],"manipulation":[13,128],"tasks":[14,84,105,129,189],"are":[15],"being":[16],"solved.":[17],"However,":[18],"harnessing":[19],"full":[21],"power":[22,92],"requires":[26,72],"large":[27],"datasets.":[28],"Online":[29],"RL":[30,49,96],"does":[31],"not":[32],"suit":[33],"itself":[34],"readily":[35],"into":[36],"this":[37,139],"paradigm":[38],"due":[39],"to":[40,55,77,100,161,205],"costly":[41],"and":[42,150,179],"time-consuming":[43],"agent-environment":[44],"interaction.":[45],"Therefore,":[46],"offline":[48,94],"algorithms":[50],"have":[51,225],"recently":[52],"been":[53],"proposed":[54],"learn":[56,78,206],"tasks.":[58,234],"But":[59],"mainly,":[60],"all":[61],"such":[62],"methods":[63,119],"focus":[64],"on":[65],"a":[66,79,207],"single-task":[67],"or":[68],"multitask":[69],"learning,":[70,214],"which":[71],"retraining":[73],"whenever":[74],"we":[75],"need":[76],"new":[80,208],"task.":[81,209],"Continuously":[82],"without":[85],"forgetting":[86,149,223],"previous":[87,198,233],"knowledge":[88,152,196,231],"combined":[89,140],"with":[90,157],"would":[97],"allow":[98],"us":[99],"scale":[101],"number":[103,175],"by":[106],"adding":[107],"them":[108],"one":[109],"after":[110],"another.":[111],"This":[112],"paper":[113],"investigates":[114],"effectiveness":[116],"regularisation-based":[118],"like":[120,215],"synaptic":[121,217],"intelligence":[122,218],"for":[123,212],"sequentially":[124,190],"image-based":[126],"in":[130,192],"an":[131],"offline-RL":[132],"setup.":[133],"We":[134,154,168,185],"evaluate":[135],"performance":[137],"framework":[141],"against":[142],"common":[143],"challenges":[144],"sequential":[146],"learning:":[147],"catastrophic":[148,222],"forward":[151],"transfer.":[153],"performed":[155],"experiments":[156],"different":[158],"task":[159,166],"combinations":[160],"analyse":[162],"effect":[164,172],"ordering.":[167],"also":[169],"investigated":[170],"object":[177],"configurations":[178],"density":[181],"robot":[183],"trajectories.":[184],"found":[186],"that":[187],"helps":[191],"retention":[194],"from":[197,232],"tasks,":[199],"thereby":[200],"reducing":[201],"time":[203],"required":[204],"Regularisation-based":[210],"approaches":[211],"continuous":[213],"method,":[219],"help":[220],"mitigate":[221],"but":[224],"shown":[226],"only":[227],"limited":[228],"transfer":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-01T08:55:55.761014","created_date":"2025-10-10T00:00:00"}
