{"id":"https://openalex.org/W4382237565","doi":"https://doi.org/10.1609/aaai.v37i7.26063","title":"Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions","display_name":"Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382237565","doi":"https://doi.org/10.1609/aaai.v37i7.26063"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v37i7.26063","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i7.26063","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26063/25835","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26063/25835","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100735692","display_name":"Qiyuan Liu","orcid":"https://orcid.org/0000-0002-8941-911X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qiyuan Liu","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100617023","display_name":"Qi Zhou","orcid":"https://orcid.org/0000-0002-6549-9362"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhou","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833239","display_name":"Rui Yang","orcid":"https://orcid.org/0000-0003-3525-1726"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Yang","raw_affiliation_strings":["University of Science and Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440047","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0002-1262-6719"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["University of Science and Technology of China\nHefei Comprehensive National Science Center"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China\nHefei Comprehensive National Science Center","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100735692"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.4353,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54690722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"37","issue":"7","first_page":"8843","last_page":"8851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.972100019454956,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.972100019454956,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9584000110626221,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9172999858856201,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.7223028540611267},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7150030136108398},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6095361709594727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6068177223205566},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5896843075752258},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5247706770896912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.523618757724762},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49490946531295776},{"id":"https://openalex.org/keywords/distraction","display_name":"Distraction","score":0.4371114671230316},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42926231026649475},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09953847527503967}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7223028540611267},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7150030136108398},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6095361709594727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068177223205566},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5896843075752258},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5247706770896912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.523618757724762},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49490946531295776},{"id":"https://openalex.org/C2776378700","wikidata":"https://www.wikidata.org/wiki/Q3030775","display_name":"Distraction","level":2,"score":0.4371114671230316},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42926231026649475},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09953847527503967},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v37i7.26063","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i7.26063","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26063/25835","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v37i7.26063","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i7.26063","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26063/25835","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5044860529","display_name":null,"funder_award_id":"WK3490000004","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6844051781","display_name":null,"funder_award_id":"00000","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382237565.pdf"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W1585160083","https://openalex.org/W1591992921","https://openalex.org/W1995688924","https://openalex.org/W2025768430","https://openalex.org/W2145339207","https://openalex.org/W2158131535","https://openalex.org/W2522489477","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2883725317","https://openalex.org/W2948210913","https://openalex.org/W2950872548","https://openalex.org/W2954974210","https://openalex.org/W2962369866","https://openalex.org/W2977481643","https://openalex.org/W2986405467","https://openalex.org/W2990321889","https://openalex.org/W2995298643","https://openalex.org/W2997101648","https://openalex.org/W2997103132","https://openalex.org/W3005680577","https://openalex.org/W3021708257","https://openalex.org/W3034246689","https://openalex.org/W3036185205","https://openalex.org/W3036224891","https://openalex.org/W3036670859","https://openalex.org/W3041890730","https://openalex.org/W3045217911","https://openalex.org/W3045991037","https://openalex.org/W3085605093","https://openalex.org/W3115293622","https://openalex.org/W3119486431","https://openalex.org/W3119908121","https://openalex.org/W3125947392","https://openalex.org/W3129170303","https://openalex.org/W3132674603","https://openalex.org/W3166705655","https://openalex.org/W3169216412","https://openalex.org/W3169292688","https://openalex.org/W3172628684","https://openalex.org/W3175182975","https://openalex.org/W3175558129","https://openalex.org/W3176598668","https://openalex.org/W3186672455","https://openalex.org/W3205321526","https://openalex.org/W3206042616","https://openalex.org/W3210788351","https://openalex.org/W3211614623","https://openalex.org/W4242401062","https://openalex.org/W4287393217","https://openalex.org/W4287667696","https://openalex.org/W4287724327","https://openalex.org/W4287811291","https://openalex.org/W4288024349","https://openalex.org/W4288294128","https://openalex.org/W4288335419","https://openalex.org/W4293378868","https://openalex.org/W4297808394","https://openalex.org/W6635516443","https://openalex.org/W6727252785","https://openalex.org/W6776867236","https://openalex.org/W6779160628","https://openalex.org/W6780523241","https://openalex.org/W6797029100"],"related_works":["https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2902347140","https://openalex.org/W2912933387","https://openalex.org/W2997669297","https://openalex.org/W4289441014","https://openalex.org/W2962823158","https://openalex.org/W4312476626","https://openalex.org/W4362598752","https://openalex.org/W3127235394"],"abstract_inverted_index":{"Recent":[0],"work":[1],"has":[2],"shown":[3],"that":[4,143,158],"representation":[5,22,148],"learning":[6,14,23,84,149],"plays":[7],"a":[8,43,85],"critical":[9],"role":[10],"in":[11,19,33,61],"sample-efficient":[12,147],"reinforcement":[13],"(RL)":[15],"from":[16],"pixels.":[17],"Unfortunately,":[18],"real-world":[20],"scenarios,":[21],"is":[24,142,183],"usually":[25],"fragile":[26],"to":[27,79,90,103],"task-irrelevant":[28,130],"distractions":[29,153],"such":[30],"as":[31,107],"variations":[32],"background":[34],"or":[35],"viewpoint.":[36],"To":[37],"tackle":[38],"this":[39],"problem,":[40],"we":[41],"propose":[42],"novel":[44],"clustering-based":[45],"approach,":[46],"namely":[47],"Clustering":[48],"with":[49,98],"Bisimulation":[50],"Metrics":[51],"(CBM),":[52],"which":[53,126],"learns":[54],"robust":[55,135],"representations":[56,122,136],"by":[57,74],"grouping":[58,72],"visual":[59,167],"observations":[60,73],"the":[62,80,91,111,119,162],"latent":[63],"space.":[64],"Specifically,":[65],"CBM":[66,102,117,144,159],"alternates":[67],"between":[68,114],"two":[69],"steps:":[70],"(1)":[71],"measuring":[75],"their":[76],"bisimulation":[77,99,108],"distances":[78],"learned":[81],"prototypes;":[82],"(2)":[83],"set":[86],"of":[87,121,165],"prototypes":[88],"according":[89],"current":[92],"cluster":[93,96],"assignments.":[94],"Computing":[95],"assignments":[97],"metrics":[100,109],"enables":[101],"capture":[104],"task-relevant":[105],"information,":[106],"quantify":[110],"behavioral":[112],"similarity":[113],"observations.":[115],"Moreover,":[116],"encourages":[118],"consistency":[120],"within":[123],"each":[124],"group,":[125],"facilitates":[127],"filtering":[128],"out":[129],"information":[131],"and":[132,170,177],"thus":[133],"induces":[134],"against":[137],"distractions.":[138],"An":[139],"appealing":[140],"feature":[141],"can":[145],"achieve":[146],"even":[150],"if":[151],"multiple":[152,176],"exist":[154],"simultaneously.":[155],"Experiments":[156],"demonstrate":[157],"significantly":[160],"improves":[161],"sample":[163],"efficiency":[164],"popular":[166],"RL":[168],"algorithms":[169],"achieves":[171],"state-of-the-art":[172],"performance":[173],"on":[174],"both":[175],"single":[178],"distraction":[179],"settings.":[180],"The":[181],"code":[182],"available":[184],"at":[185],"https://github.com/MIRALab-USTC/RL-CBM.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}