{"id":"https://openalex.org/W7043064335","doi":null,"title":"Reinforcement Learning in Partially Observable Markov Decision Processes: Learning to Remember the Past by Learning to Predict the Future","display_name":"Reinforcement Learning in Partially Observable Markov Decision Processes: Learning to Remember the Past by Learning to Predict the Future","publication_year":2025,"publication_date":"2025-04-07","ids":{"openalex":"https://openalex.org/W7043064335"},"language":"en","primary_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/328700","doi":null,"is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/328700","pdf_url":"https://orbi.uliege.be/bitstream/2268/328700/1/rl-in-pomdp.pdf","source":{"id":"https://openalex.org/S4306401300","display_name":"ORBi (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.uliege.be/bitstream/2268/328700/1/rl-in-pomdp.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052505881","display_name":"Gaspard Lambrechts","orcid":"https://orcid.org/0009-0002-6378-5186","observed_orcids":["https://orcid.org/0009-0002-6378-5186"]},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Lambrechts, Gaspard","raw_affiliation_strings":["Universit\u00e9 de Li\u00e8ge - ULi\u00e8ge > Montefiore Institute of Electrical Engineering and Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Li\u00e8ge - ULi\u00e8ge > Montefiore Institute of Electrical Engineering and Computer Science","institution_ids":["https://openalex.org/I157674565"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5052505881"],"corresponding_institution_ids":["https://openalex.org/I157674565"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9259999990463257},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8349999785423279},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.7889999747276306},{"id":"https://openalex.org/keywords/long-term-memory","display_name":"long-term memory","score":0.718999981880188},{"id":"https://openalex.org/keywords/belief-representation","display_name":"belief representation","score":0.5879999995231628},{"id":"https://openalex.org/keywords/trajectory-generation","display_name":"trajectory generation","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508000254631042},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.299699991941452},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29760000109672546},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:orbi.ulg.ac.be:2268/328700","doi":null,"is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/328700","pdf_url":"https://orbi.uliege.be/bitstream/2268/328700/1/rl-in-pomdp.pdf","source":{"id":"https://openalex.org/S4306401300","display_name":"ORBi (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"}],"best_oa_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/328700","doi":null,"is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/328700","pdf_url":"https://orbi.uliege.be/bitstream/2268/328700/1/rl-in-pomdp.pdf","source":{"id":"https://openalex.org/S4306401300","display_name":"ORBi (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"http://purl.org/coar/resource_type/c_db06"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7043064335.pdf","grobid_xml":"https://content.openalex.org/works/W7043064335.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1779483307","https://openalex.org/W1810943226","https://openalex.org/W1924770834","https://openalex.org/W2173248099","https://openalex.org/W2291973609","https://openalex.org/W2510842514","https://openalex.org/W2607713949","https://openalex.org/W2781585732","https://openalex.org/W2786019934","https://openalex.org/W2786406400","https://openalex.org/W2797349519","https://openalex.org/W2900559324","https://openalex.org/W2954559956","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2981030070","https://openalex.org/W2986603352","https://openalex.org/W3119469378","https://openalex.org/W4226528802","https://openalex.org/W4385261004","https://openalex.org/W4389326242","https://openalex.org/W4391505291","https://openalex.org/W4399912834","https://openalex.org/W4405918587","https://openalex.org/W4407091303","https://openalex.org/W4407949397","https://openalex.org/W4409147637","https://openalex.org/W4411607431"],"related_works":["https://openalex.org/W7097345780","https://openalex.org/W2185008334","https://openalex.org/W6962511018","https://openalex.org/W3208926142","https://openalex.org/W4388574051","https://openalex.org/W3038057344","https://openalex.org/W4413766826","https://openalex.org/W2290302229","https://openalex.org/W2794752562","https://openalex.org/W3097296058"],"abstract_inverted_index":{"Intelligence":[0],"is":[1,22,307],"usually":[2],"understood":[3],"as":[4,132,277],"the":[5,30,64,75,78,82,120,125,129,133,142,175,217,230,304,318,328],"ability":[6,143],"to":[7,15,113,144,180,267,284,309,311,333],"make":[8,312],"decisions,":[9],"based":[10],"on":[11,35,42,274],"perception,":[12,67],"in":[13,45,117,287],"order":[14],"achieve":[16],"objectives.":[17],"In":[18,57,317],"other":[19],"words,":[20],"intelligence":[21],"about":[23,29,174],"perceiving":[24],"and":[25,62,71,94,103,207,239],"abstracting":[26],"past":[27],"information":[28,173,202],"world":[31,176,197,247,279],"for":[32,51,153,216,245],"then":[33],"acting":[34],"its":[36],"future":[37],"execution.":[38],"This":[39],"thesis":[40,83,295,325],"focuses":[41],"reinforcement":[43],"learning":[44,52,98,112,187,300,310],"partially":[46],"observable":[47],"Markov":[48],"decision":[49],"processes":[50],"intelligent":[53,99,146,182],"behaviors":[54,100,183],"through":[55,289],"interaction.":[56],"particular,":[58],"this":[59,200,227,294,324],"manuscript":[60],"explores":[61,170],"emphasizes":[63],"interplay":[65],"between":[66],"representations,":[68],"memory,":[69],"predictions":[70],"decisions.":[72],"After":[73],"introducing":[74],"theoretical":[76,214],"foundations,":[77],"core":[79],"contributions":[80],"of":[81,119,221,303,320],"are":[84,282],"presented":[85],"across":[86,337],"three":[87],"thematic":[88],"parts.":[89],"The":[90,164,234],"first":[91],"part,":[92,166,236],"\u201cLearning":[93],"Remembering,\u201d":[95],"investigates":[96],"how":[97,111,138,171,299],"improves":[101,141],"memory":[102,140],"vice":[104],"versa.":[105],"To":[106],"begin":[107],"with,":[108],"it":[109,136,211,254,272],"studies":[110,137],"act":[114],"optimally":[115],"results":[116],"representations":[118,206,302],"perception":[121,189,305],"history":[122,205,306],"that":[123,157,196,225,249,259,281],"encode":[124],"posterior":[126],"distribution":[127],"over":[128],"states,":[130],"known":[131],"belief.":[134],"Next,":[135],"long-term":[139,161],"learn":[145,181],"behaviors,":[147],"by":[148,193,297],"designing":[149],"an":[150],"initialization":[151],"procedure":[152],"recurrent":[154,266],"neural":[155],"networks":[156],"endows":[158],"them":[159],"with":[160],"memorization":[162],"abilities.":[163],"second":[165],"\u201cLeveraging":[167],"Additional":[168],"Information,\u201d":[169],"additional":[172,201],"can":[177],"be":[178],"used":[179],"faster":[184,208],"than":[185],"when":[186],"from":[188,330],"only.":[190],"It":[191],"starts":[192],"empirically":[194],"showing":[195],"models":[198,248,258,280],"predicting":[199],"provide":[203],"better":[204],"learning.":[209],"Then,":[210],"provides":[212],"a":[213,222],"justification":[215],"improved":[218],"convergence":[219],"speed":[220],"particular":[223],"algorithm":[224],"leverages":[226],"information,":[228],"namely":[229],"asymmetric":[231],"actor-critic":[232],"algorithm.":[233],"third":[235],"\u201cEntangling":[237],"Predictions":[238],"Decisions,\u201d":[240],"proposes":[241],"several":[242],"architectural":[243],"innovations":[244],"obtaining":[246],"efficiently":[250],"generate":[251,285],"trajectories.":[252],"First,":[253],"develops":[255],"new":[256,278],"sequence":[257],"parallelize":[260],"autoregressive":[261],"generation,":[262],"while":[263],"being":[264],"implicitly":[265],"allow":[268],"resuming":[269],"generation.":[270],"Afterwards,":[271],"elaborates":[273],"their":[275],"use":[276],"able":[283],"trajectories":[286],"parallel":[288],"specific":[290],"latent":[291],"policies.":[292],"Finally,":[293],"concludes":[296],"summarizing":[298],"adequate":[301],"paramount":[308],"decisions":[313],"under":[314],"partial":[315],"observability.":[316],"perspective":[319],"developing":[321],"general":[322],"intelligence,":[323],"also":[326],"motivates":[327],"shift":[329],"specialized":[331],"abstractions":[332,335],"generalizable":[334],"extending":[336],"diverse":[338],"environments.":[339]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}