{"id":"https://openalex.org/W4415524614","doi":"https://doi.org/10.1109/mlsp62443.2025.11204264","title":"State Prediction for Offline Reinforcement Learning via Sequence-to-Sequence Modeling","display_name":"State Prediction for Offline Reinforcement Learning via Sequence-to-Sequence Modeling","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524614","doi":"https://doi.org/10.1109/mlsp62443.2025.11204264"},"language":null,"primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"article","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/A5043498534","display_name":"Abdelghani Ghanem","orcid":"https://orcid.org/0000-0003-0273-772X"},"institutions":[{"id":"https://openalex.org/I4210106663","display_name":"International University of Rabat","ror":"https://ror.org/01t9czq80","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210106663"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Abdelghani Ghanem","raw_affiliation_strings":["International University of Rabat,TICLab, College of Engineering and Architecture,Morocco"],"affiliations":[{"raw_affiliation_string":"International University of Rabat,TICLab, College of Engineering and Architecture,Morocco","institution_ids":["https://openalex.org/I4210106663"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057324156","display_name":"Mounir Ghogho","orcid":"https://orcid.org/0000-0002-0055-7867"},"institutions":[{"id":"https://openalex.org/I4210131560","display_name":"Universit\u00e9 Mohammed VI Polytechnique","ror":"https://ror.org/03xc55g68","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210131560"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Mounir Ghogho","raw_affiliation_strings":["University Mohammed VI Polytechnic,College of Computing,Morocco"],"affiliations":[{"raw_affiliation_string":"University Mohammed VI Polytechnic,College of Computing,Morocco","institution_ids":["https://openalex.org/I4210131560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032860990","display_name":"Philippe Ciblat","orcid":"https://orcid.org/0000-0002-2310-4115"},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Philippe Ciblat","raw_affiliation_strings":["Institut Polytechnique de Paris,LTCI,Department of Image, Data, Signal, Telecom Paris,France"],"affiliations":[{"raw_affiliation_string":"Institut Polytechnique de Paris,LTCI,Department of Image, Data, Signal, Telecom Paris,France","institution_ids":["https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5043498534"],"corresponding_institution_ids":["https://openalex.org/I4210106663"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17008768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9735999703407288,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9735999703407288,"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":0.9718000292778015,"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":0.8686000108718872},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5048999786376953},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4871000051498413},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.44429999589920044},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4309999942779541},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41019999980926514},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.39399999380111694},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3824999928474426},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3691999912261963}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8686000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6879000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6656000018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5983999967575073},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3400999903678894},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C183560197","wikidata":"https://www.wikidata.org/wiki/Q7247302","display_name":"Process state","level":3,"score":0.33480000495910645},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C76956256","wikidata":"https://www.wikidata.org/wiki/Q27610560","display_name":"Process modeling","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29019999504089355},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25600001215934753},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204264","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2964021598","https://openalex.org/W4375869380","https://openalex.org/W4385245566","https://openalex.org/W4387869694","https://openalex.org/W4392903325","https://openalex.org/W4392903533","https://openalex.org/W4404037281","https://openalex.org/W4404037473","https://openalex.org/W4404037515","https://openalex.org/W4404037585","https://openalex.org/W4404037589"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"offline":[1,86],"reinforcement":[2,87],"learning":[3,88],"methods":[4,171],"often":[5],"frame":[6],"the":[7,28,36,44,50,74,106,110,135,139,147,180],"problem":[8],"as":[9,43,89],"a":[10,15,23,63,71,90,130,173],"sequence":[11,163],"modeling":[12,58,92,164],"task,":[13],"employing":[14],"decoder-only":[16,151],"architecture":[17,83],"to":[18],"process":[19],"states,":[20],"actions,":[21],"and":[22,49,59,166],"single":[24],"scalar":[25,51],"value":[26],"representing":[27],"sum":[29],"of":[30,39,46,53,101,112,121,126,141,149,175],"future":[31,127],"rewards":[32],"(i.e.,":[33],"returns).":[34],"However,":[35],"distinct":[37],"characteristics":[38],"these":[40],"modalities,":[41,143],"such":[42],"non-smoothness":[45],"action":[47,97,113],"sequences":[48,125],"nature":[52],"returns,":[54,128],"may":[55],"hinder":[56],"effective":[57],"optimization":[60],"when":[61],"using":[62],"shared":[64,150],"architecture.":[65],"In":[66],"this":[67],"work,":[68],"we":[69],"propose":[70],"divide-and-conquer":[72],"strategy,":[73],"Reward-Guided":[75],"Decision":[76],"Translator":[77],"(RGDT),":[78],"that":[79,156],"leverages":[80],"an":[81],"encoder-decoder":[82],"by":[84,109],"casting":[85],"sequence-to-sequence":[91],"problem.":[93],"Our":[94],"approach":[95,145],"foregoes":[96],"prediction":[98],"in":[99],"favor":[100],"next":[102],"state":[103,122],"prediction,":[104],"mitigating":[105],"challenges":[107],"posed":[108],"nonsmoothness":[111],"sequences.":[114],"Furthermore,":[115],"our":[116,144,157],"formulation":[117],"enables":[118],"direct":[119],"conditioning":[120],"generation":[123],"on":[124],"providing":[129],"more":[131],"informative":[132],"signal":[133],"for":[134],"model.":[136],"By":[137],"disentangling":[138],"processing":[140],"different":[142],"addresses":[146],"limitations":[148],"architectures.":[152],"Empirical":[153],"results":[154],"demonstrate":[155],"method":[158],"significantly":[159],"outperforms":[160],"existing":[161],"generative":[162],"techniques":[165],"matches":[167],"or":[168],"surpasses":[169],"state-of-the-art":[170],"across":[172],"range":[174],"continuous":[176],"control":[177],"tasks":[178],"from":[179],"D4RL":[181],"benchmark.":[182]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}