{"id":"https://openalex.org/W4406089982","doi":"https://doi.org/10.1109/tip.2024.3523798","title":"Constrained Visual Representation Learning With Bisimulation Metrics for Safe Reinforcement Learning","display_name":"Constrained Visual Representation Learning With Bisimulation Metrics for Safe Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4406089982","doi":"https://doi.org/10.1109/tip.2024.3523798","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030877"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2024.3523798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3523798","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100733180","display_name":"Rongrong Wang","orcid":"https://orcid.org/0000-0003-0615-0838"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-0615-0838","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091364297","display_name":"Yuhu Cheng","orcid":"https://orcid.org/0000-0003-2022-9999"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhu Cheng","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-2022-9999","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108064895","display_name":"Xuesong Wang","orcid":"https://orcid.org/0000-0002-5327-1088"},"institutions":[{"id":"https://openalex.org/I25757504","display_name":"China University of Mining and Technology","ror":"https://ror.org/01xt2dr21","country_code":"CN","type":"education","lineage":["https://openalex.org/I25757504"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuesong Wang","raw_affiliation_strings":["Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5327-1088","affiliations":[{"raw_affiliation_string":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China","institution_ids":["https://openalex.org/I25757504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25757504"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00137287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"379","last_page":"393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9731000065803528,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9731000065803528,"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":0.9455999732017517,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9362999796867371,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.8156188726425171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6479215621948242},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.5983197689056396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5963555574417114},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5930724143981934},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5665844082832336},{"id":"https://openalex.org/keywords/bisimulation","display_name":"Bisimulation","score":0.4407581388950348},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4311584532260895},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4178483188152313},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.24835345149040222},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12841856479644775}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8156188726425171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6479215621948242},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.5983197689056396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5963555574417114},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5930724143981934},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5665844082832336},{"id":"https://openalex.org/C135315306","wikidata":"https://www.wikidata.org/wiki/Q866364","display_name":"Bisimulation","level":2,"score":0.4407581388950348},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4311584532260895},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4178483188152313},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.24835345149040222},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12841856479644775},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2024.3523798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2024.3523798","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:40030877","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030877","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G4756161396","display_name":null,"funder_award_id":"62176259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4823360002","display_name":null,"funder_award_id":"62373364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6172462902","display_name":null,"funder_award_id":"BE2022095","funder_id":"https://openalex.org/F4320327780","funder_display_name":"Key Research and Development Program of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327780","display_name":"Key Research and Development Program of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1518931405","https://openalex.org/W1995688924","https://openalex.org/W2058735307","https://openalex.org/W2168359464","https://openalex.org/W2736601468","https://openalex.org/W2842511635","https://openalex.org/W2974886567","https://openalex.org/W2979211489","https://openalex.org/W2997101648","https://openalex.org/W3093210455","https://openalex.org/W3155402581","https://openalex.org/W3162902207","https://openalex.org/W3175558129","https://openalex.org/W3187179100","https://openalex.org/W3195968524","https://openalex.org/W3208857029","https://openalex.org/W3209936399","https://openalex.org/W4211103897","https://openalex.org/W4252279978","https://openalex.org/W4281480521","https://openalex.org/W4285214186","https://openalex.org/W4293999331","https://openalex.org/W4297808394","https://openalex.org/W4304731240","https://openalex.org/W4306824019","https://openalex.org/W4311486598","https://openalex.org/W4385245566","https://openalex.org/W4387197152","https://openalex.org/W6635516443","https://openalex.org/W6638018090","https://openalex.org/W6687063787","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6744627333","https://openalex.org/W6747473740","https://openalex.org/W6763088550","https://openalex.org/W6765407481","https://openalex.org/W6768617876","https://openalex.org/W6771280675","https://openalex.org/W6774126978","https://openalex.org/W6776901495","https://openalex.org/W6779827379","https://openalex.org/W6809864479","https://openalex.org/W6838701874","https://openalex.org/W6839804929","https://openalex.org/W6842566449","https://openalex.org/W6846052559","https://openalex.org/W6846515144"],"related_works":["https://openalex.org/W2971351794","https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2101991911","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W1925875298","https://openalex.org/W4292701710"],"abstract_inverted_index":{"Safe":[0,162],"reinforcement":[1,58,150],"learning":[2,52,59,151],"aims":[3],"to":[4,69,84,95,109,126],"ensure":[5],"the":[6,29,39,48,86,97,110,160,187],"optimal":[7],"performance":[8],"while":[9,37,134],"minimizing":[10],"potential":[11],"risks.":[12],"In":[13],"real-world":[14],"applications,":[15],"especially":[16],"in":[17,28,153,181],"scenarios":[18],"that":[19,144],"rely":[20],"on":[21,140],"visual":[22,50,72,131],"inputs,":[23],"a":[24,63,167,172,178],"key":[25],"challenge":[26],"lies":[27],"extraction":[30],"of":[31,189],"essential":[32],"features":[33],"for":[34,56],"safe":[35,57,149],"decision-making":[36],"maintaining":[38],"sample":[40],"efficiency.":[41],"To":[42],"address":[43],"this":[44],"issue,":[45],"we":[46],"propose":[47],"constrained":[49],"representation":[51],"with":[53],"bisimulation":[54,80,112],"metrics":[55,81],"(CVRL-BM).":[60],"CVRL-BM":[61,123,145,158],"constructs":[62],"sequential":[64],"conditional":[65],"variational":[66],"inference":[67],"model":[68],"compress":[70],"high-dimensional":[71],"observations":[73],"into":[74],"low-dimensional":[75],"state":[76,103,132],"representations.":[77],"Additionally,":[78],"safety":[79,111,137,154],"are":[82],"introduced":[83],"quantify":[85],"behavioral":[87],"similarity":[88],"between":[89,99,114],"states,":[90],"and":[91,129,155,177],"our":[92,190],"objective":[93],"is":[94,124],"make":[96],"distance":[98],"any":[100],"two":[101,121],"latent":[102],"representations":[104,133],"as":[105,107],"close":[106],"possible":[108],"metric":[113],"their":[115],"corresponding":[116],"states.":[117],"By":[118],"integrating":[119],"these":[120],"components,":[122],"able":[125],"learn":[127],"compact":[128],"information-rich":[130],"satisfying":[135],"pre-defined":[136],"constraints.":[138],"Experiments":[139],"Safety":[141],"Gym":[142],"show":[143],"outperforms":[146],"existing":[147],"vision-based":[148],"methods":[152],"efficacy.":[156],"Particularly,":[157],"surpasses":[159],"state-of-the-art":[161],"SLAC":[163],"method":[164],"by":[165],"achieving":[166],"19.748%":[168],"higher":[169],"reward":[170],"return,":[171,176],"41.772%":[173],"lower":[174],"cost":[175,182],"5.027%":[179],"decrease":[180],"regret.":[183],"These":[184],"results":[185],"highlight":[186],"effectiveness":[188],"proposed":[191],"CVRL-BM.":[192]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}