{"id":"https://openalex.org/W4285607107","doi":"https://doi.org/10.24963/ijcai.2022/514","title":"Don\u2019t Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning","display_name":"Don\u2019t Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285607107","doi":"https://doi.org/10.24963/ijcai.2022/514"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/514","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/514","pdf_url":"https://www.ijcai.org/proceedings/2022/0514.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0514.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064339172","display_name":"Zhecheng Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhecheng Yuan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100899722","display_name":"Guozheng Ma","orcid":"https://orcid.org/0000-0003-1884-6103"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guozheng Ma","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109243996","display_name":"Yao Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yao Mu","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044226655","display_name":"Bo Xia","orcid":"https://orcid.org/0000-0001-7694-4743"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xia","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032061647","display_name":"Bo Yuan","orcid":"https://orcid.org/0000-0003-2169-0007"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yuan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100737123","display_name":"Xueqian Wang","orcid":"https://orcid.org/0000-0002-8632-6073"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqian Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752686","display_name":"Ping Luo","orcid":"https://orcid.org/0000-0002-6685-7950"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ping Luo","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049093671","display_name":"Huazhe Xu","orcid":"https://orcid.org/0000-0001-8578-1261"},"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":true,"raw_author_name":"Huazhe Xu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5049093671"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":1.7654,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86917572,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3702","last_page":"3708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9925000071525574,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9896000027656555,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.811501145362854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7660021185874939},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.701528787612915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.624871551990509},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.6217308640480042},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6013768315315247},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.556850790977478},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5284678339958191},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.472187876701355},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4429016709327698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41249480843544006},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1651909053325653}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.811501145362854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7660021185874939},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.701528787612915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.624871551990509},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.6217308640480042},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6013768315315247},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.556850790977478},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5284678339958191},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.472187876701355},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4429016709327698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41249480843544006},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1651909053325653},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2022/514","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/514","pdf_url":"https://www.ijcai.org/proceedings/2022/0514.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/514","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/514","pdf_url":"https://www.ijcai.org/proceedings/2022/0514.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285607107.pdf","grobid_xml":"https://content.openalex.org/works/W4285607107.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1995688924","https://openalex.org/W2145339207","https://openalex.org/W2605102758","https://openalex.org/W2797527950","https://openalex.org/W2898436992","https://openalex.org/W2954996726","https://openalex.org/W2962887844","https://openalex.org/W2994073215","https://openalex.org/W3021708257","https://openalex.org/W3035060554","https://openalex.org/W3036619998","https://openalex.org/W3041404693","https://openalex.org/W3125947392","https://openalex.org/W3172628684","https://openalex.org/W3175182975","https://openalex.org/W3185441898","https://openalex.org/W3205321526","https://openalex.org/W3214048558","https://openalex.org/W4287811291","https://openalex.org/W4289667030","https://openalex.org/W4295719664","https://openalex.org/W4297789758"],"related_works":["https://openalex.org/W3185235544","https://openalex.org/W4297791327","https://openalex.org/W2897842840","https://openalex.org/W2911623553","https://openalex.org/W2397777611","https://openalex.org/W1502031429","https://openalex.org/W2318923278","https://openalex.org/W2417585376","https://openalex.org/W1994157709","https://openalex.org/W2797811993"],"abstract_inverted_index":{"One":[0],"of":[1,38,46,79,94,133],"the":[2,35,44,67,73,77,83,92,114,124,131],"key":[3],"challenges":[4],"in":[5,33,57,91],"visual":[6,109,166],"Reinforcement":[7],"Learning":[8],"(RL)":[9],"is":[10,82],"to":[11,17,43],"learn":[12],"policies":[13],"that":[14,150],"can":[15],"generalize":[16],"unseen":[18],"environments.":[19],"Recently,":[20],"data":[21,27,51],"augmentation":[22],"techniques":[23],"aiming":[24],"at":[25],"enhancing":[26],"diversity":[28],"have":[29],"demonstrated":[30],"proven":[31],"performance":[32],"improving":[34],"generalization":[36,74],"ability":[37],"learned":[39],"policies.":[40],"However,":[41],"due":[42],"sensitivity":[45],"RL":[47],"training,":[48],"naively":[49],"applying":[50],"augmentation,":[52],"which":[53,111],"transforms":[54],"each":[55],"pixel":[56],"a":[58],"task-agnostic":[59],"manner,":[60],"may":[61],"suffer":[62],"from":[63],"instability":[64],"and":[65,87,121,141,156],"damage":[66],"sample":[68,154],"efficiency,":[69],"thus":[70],"further":[71],"exacerbating":[72],"performance.":[75],"At":[76],"heart":[78],"this":[80,99],"phenomenon":[81],"diverged":[84],"action":[85],"distribution":[86],"high-variance":[88],"value":[89],"estimation":[90],"face":[93],"augmented":[95],"images.":[96],"To":[97],"alleviate":[98],"issue,":[100],"we":[101],"propose":[102],"Task-aware":[103],"Lipschitz":[104,119],"Data":[105],"Augmentation":[106],"(TLDA)":[107],"for":[108,127],"RL,":[110],"explicitly":[112],"identifies":[113],"task-correlated":[115],"pixels":[116,126],"with":[117],"large":[118],"constants,":[120],"only":[122],"augments":[123],"task-irrelevant":[125],"stability.":[128],"We":[129],"verify":[130],"effectiveness":[132],"our":[134],"approach":[135],"on":[136],"DeepMind":[137,142],"Control":[138],"suite,":[139],"CARLA":[140],"Manipulation":[143],"tasks.":[144],"The":[145],"extensive":[146],"empirical":[147],"results":[148],"show":[149],"TLDA":[151],"improves":[152],"both":[153],"efficiency":[155],"generalization;":[157],"it":[158],"outperforms":[159],"previous":[160],"state-of-the-art":[161],"methods":[162],"across":[163],"3":[164],"different":[165],"control":[167],"benchmarks.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}