{"id":"https://openalex.org/W4402352911","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651374","title":"Delayed MDPs with Feature Mapping","display_name":"Delayed MDPs with Feature Mapping","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352911","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651374"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651374","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5104049478","display_name":"Jialin Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jialin Dong","raw_affiliation_strings":["University of California,Los Angeles,CA,US,90095"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles,CA,US,90095","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100449260","display_name":"Jiayi Wang","orcid":"https://orcid.org/0000-0002-1313-138X"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Wang","raw_affiliation_strings":["The University of Utah,Salt Lake City,UT,US,84112"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Utah,Salt Lake City,UT,US,84112","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072096775","display_name":"Lin F. Yang","orcid":"https://orcid.org/0000-0003-4602-3366"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin F. Yang","raw_affiliation_strings":["University of California,Los Angeles,CA,US,90095"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Los Angeles,CA,US,90095","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"228","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T10142","display_name":"Formal Methods in Verification","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7136867642402649},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5888000130653381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7136867642402649},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651374","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1589577058","https://openalex.org/W1867103660","https://openalex.org/W1973734200","https://openalex.org/W1977655452","https://openalex.org/W1980722163","https://openalex.org/W1988098342","https://openalex.org/W2096750723","https://openalex.org/W2117864026","https://openalex.org/W2121863487","https://openalex.org/W2159566498","https://openalex.org/W2344786740","https://openalex.org/W2914304175","https://openalex.org/W2959895084","https://openalex.org/W2963600139","https://openalex.org/W2963898834","https://openalex.org/W2974778612","https://openalex.org/W3020125231","https://openalex.org/W3115949757","https://openalex.org/W4226261869","https://openalex.org/W4240729697","https://openalex.org/W6631500254","https://openalex.org/W6632504492","https://openalex.org/W6639039794","https://openalex.org/W6678092311","https://openalex.org/W6683841709","https://openalex.org/W6713133303","https://openalex.org/W6729229454","https://openalex.org/W6735939104","https://openalex.org/W6763257922","https://openalex.org/W6763329203","https://openalex.org/W6768843968","https://openalex.org/W6769434015","https://openalex.org/W6769467942","https://openalex.org/W6774376309","https://openalex.org/W6780209122","https://openalex.org/W6789246195","https://openalex.org/W6810463583"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Modern":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"frequently":[4],"suffers":[5],"from":[6,78],"large":[7,29],"state":[8,30,77,82,130,251],"and":[9,12,31,58,83,131,151,195,238,252],"action":[10,32,85,90,132,163,253],"spaces":[11],"delayed":[13,54,62,119,232],"feedback":[14,55,233],"in":[15,50],"the":[16,37,42,61,64,74,79,84,117,128,136,143,157,162,191,198,204,228,235,247,250],"environment.":[17],"Recently,":[18],"feature":[19,48,67],"mapping":[20,49,68],"has":[21],"become":[22],"an":[23,51],"effective":[24],"tool":[25],"to":[26,40,102,115,155],"deal":[27],"with":[28,53,124],"spaces,":[33],"where":[34,188],"agents":[35],"use":[36],"given":[38],"features":[39,194],"parameterize":[41],"high-dimensional":[43],"value":[44],"functions.":[45],"However,":[46],"applying":[47],"environment":[52,76],"is":[56,113,169,190,197,244],"challenging":[57],"unsolved.":[59],"In":[60,106],"environment,":[63],"utilization":[65],"of":[66,73,138,193,231,246,249],"relies":[69],"on":[70,127,234],"careful":[71],"inference":[72],"current":[75],"agent\u2019s":[80,236],"observation":[81,129],"sequence.":[86,133],"Herein,":[87],"two":[88],"consecutive":[89],"sequences":[91],"have":[92],"overlapping":[93,144],"actions,":[94,145],"which":[95],"challenges":[96],"random-theory-based":[97],"theoretical":[98,219],"regret":[99,167,241],"analysis":[100,220],"due":[101],"their":[103],"intricate":[104],"dependence.":[105],"this":[107],"paper,":[108],"a":[109,148,152,240],"new":[110],"feature-mapping-based":[111],"framework":[112],"proposed":[114,224],"solve":[116],"constant":[118],"Markov":[120],"Decision":[121],"Processes":[122],"(CDMDPs)":[123],"m-time-step-delay":[125],"based":[126],"To":[134],"address":[135],"challenge":[137],"statistical":[139,158],"coherence":[140,159],"brought":[141,160],"by":[142,161],"we":[146],"design":[147],"parameterized-transition":[149],"CDMDP":[150],"novel":[153],"method":[154],"decouple":[156],"sequences.":[164],"The":[165,218],"algorithm\u2019s":[166],"bound":[168,206,242],"$\\tilde":[170],"O\\left(":[171],"{\\left(":[172],"{d":[173],"+":[174],"2":[175],"-":[176,183,213],"{\\gamma":[177],"^m}}":[178],"\\right)\\sqrt":[179],"T":[180,210],"/{{\\left(":[181,211],"{1":[182,212],"\\gamma":[184,214],"}":[185,215],"\\right)}^2}}":[186],"\\right)$":[187],"d":[189],"number":[192],"\u03b3":[196],"discount":[199],"factor.":[200],"It":[201],"also":[202],"approaches":[203],"lower":[205],"$\\Omega":[207],"\\left(":[208],"{d\\sqrt":[209],"\\right)}^{\\frac{3}{2}}}}":[216],"\\right)$.":[217],"demonstrates":[221],"that":[222,243],"our":[223],"algorithm":[225],"effectively":[226],"alleviates":[227],"adverse":[229],"impact":[230],"decision-making,":[237],"yields":[239],"independent":[245],"size":[248],"spaces.":[254]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}