{"id":"https://openalex.org/W4387185318","doi":"https://doi.org/10.3233/faia230548","title":"Improving Visual Reinforcement Learning with Discrete Information Bottleneck Approach","display_name":"Improving Visual Reinforcement Learning with Discrete Information Bottleneck Approach","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185318","doi":"https://doi.org/10.3233/faia230548"},"language":"en","primary_location":{"id":"doi:10.3233/faia230548","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230548","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230548","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230548","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038214042","display_name":"Haitao Wang","orcid":"https://orcid.org/0000-0002-8394-6410"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102755158","display_name":"Hejun Wu","orcid":"https://orcid.org/0000-0001-9758-5698"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hejun Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102755158"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34424337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9732000231742859,"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":0.9732000231742859,"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/T10691","display_name":"Retinal Development and Disorders","score":0.9674000144004822,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10427","display_name":"Visual perception and processing mechanisms","score":0.9480999708175659,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7889777421951294},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906675100326538},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6558697819709778},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6405227780342102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5415916442871094},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.5006558895111084},{"id":"https://openalex.org/keywords/information-bottleneck-method","display_name":"Information bottleneck method","score":0.47693079710006714},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4386771619319916},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4180009663105011},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4174744188785553},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21722206473350525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1715123951435089},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.09163933992385864}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7889777421951294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906675100326538},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6558697819709778},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6405227780342102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415916442871094},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.5006558895111084},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.47693079710006714},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4386771619319916},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4180009663105011},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4174744188785553},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21722206473350525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1715123951435089},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.09163933992385864},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230548","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230548","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230548","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230548","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230548","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230548","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3373226507","display_name":null,"funder_award_id":"62272497","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185318.pdf","grobid_xml":"https://content.openalex.org/works/W4387185318.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1686946872","https://openalex.org/W2096733369","https://openalex.org/W2266728343","https://openalex.org/W2557579533","https://openalex.org/W2563830277","https://openalex.org/W2593814746","https://openalex.org/W2752796333","https://openalex.org/W2781726626","https://openalex.org/W2842511635","https://openalex.org/W2896457183","https://openalex.org/W2900152462","https://openalex.org/W2906007967","https://openalex.org/W2920362155","https://openalex.org/W2949545198","https://openalex.org/W2950365520","https://openalex.org/W2951736998","https://openalex.org/W2954974210","https://openalex.org/W2954989419","https://openalex.org/W2963009616","https://openalex.org/W2963799213","https://openalex.org/W2977481643","https://openalex.org/W2987283559","https://openalex.org/W2992977009","https://openalex.org/W2994929655","https://openalex.org/W2995298643","https://openalex.org/W3005680577","https://openalex.org/W3015437096","https://openalex.org/W3021708257","https://openalex.org/W3023640063","https://openalex.org/W3035524453","https://openalex.org/W3036619998","https://openalex.org/W3041890730","https://openalex.org/W3085605093","https://openalex.org/W3091507139","https://openalex.org/W3099206234","https://openalex.org/W3115293622","https://openalex.org/W3122690883","https://openalex.org/W3127235394","https://openalex.org/W3129529935","https://openalex.org/W3175558129","https://openalex.org/W3186672455","https://openalex.org/W3206005330","https://openalex.org/W3210788351","https://openalex.org/W4221160484","https://openalex.org/W4287256992","https://openalex.org/W4287667696","https://openalex.org/W4287724327","https://openalex.org/W4287811291","https://openalex.org/W4288294128","https://openalex.org/W4289294484","https://openalex.org/W4293469690","https://openalex.org/W4297808394","https://openalex.org/W4315706776"],"related_works":["https://openalex.org/W1504394672","https://openalex.org/W2622284819","https://openalex.org/W3089381707","https://openalex.org/W3034190530","https://openalex.org/W2741297526","https://openalex.org/W4295728955","https://openalex.org/W3129794609","https://openalex.org/W2949033103","https://openalex.org/W2304083841","https://openalex.org/W2362448732"],"abstract_inverted_index":{"Contrastive":[0],"learning":[1,14,47,99,114],"has":[2],"been":[3],"used":[4],"to":[5,84,97],"learn":[6],"useful":[7],"low-dimensional":[8],"state":[9,17,103,136],"representations":[10,18],"in":[11,100,116,145,163],"visual":[12,25,156],"reinforcement":[13],"(RL).":[15],"Such":[16,39],"substantially":[19],"improve":[20],"the":[21,34,43,90,102,132,146,151],"sample":[22,123,168],"efficiency":[23,124],"of":[24,36,79,92,134,138,165],"RL.":[26],"Nevertheless,":[27],"existing":[28],"contrastive":[29,46,60,98],"learning-based":[30,61],"RL":[31,62,157],"methods":[32,63],"have":[33],"problem":[35],"unstable":[37],"training.":[38],"instability":[40],"comes":[41],"from":[42],"fact":[44],"that":[45],"requires":[48],"an":[49,77],"extremely":[50],"large":[51],"batch":[52,68,128],"size":[53,69],"(e.g.,":[54,70],"4096":[55],"or":[56],"larger),":[57],"while":[58],"current":[59],"typically":[64],"set":[65],"a":[66,126],"small":[67,127],"512).":[71],"In":[72,150],"this":[73,86,109],"paper,":[74],"we":[75],"propose":[76],"approach":[78],"discrete":[80,106,110,135],"information":[81,95],"bottleneck":[82,96],"(DIB)":[83],"address":[85],"problem.":[87],"DIB":[88,139,153],"applies":[89],"technique":[91],"discretization":[93],"and":[94,121,161,167],"representing":[101],"with":[104,125],"concise":[105],"representation.":[107],"Using":[108],"representation":[111,137],"for":[112],"policy":[113],"results":[115],"more":[117],"stable":[118],"algorithm":[119],"training":[120],"higher":[122],"size.":[129],"We":[130],"demonstrate":[131],"advantage":[133],"on":[140],"several":[141],"continuous":[142],"control":[143],"tasks":[144],"DeepMind":[147],"Control":[148],"suite.":[149],"experiments,":[152],"outperforms":[154],"prior":[155],"methods,":[158],"both":[159],"model-based":[160],"model-free,":[162],"terms":[164],"performance":[166],"efficiency.":[169]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}