{"id":"https://openalex.org/W3005829072","doi":"https://doi.org/10.1109/icpr48806.2021.9412601","title":"Trajectory representation learning for Multi-Task NMRDP planning","display_name":"Trajectory representation learning for Multi-Task NMRDP planning","publication_year":2021,"publication_date":"2021-01-10","ids":{"openalex":"https://openalex.org/W3005829072","doi":"https://doi.org/10.1109/icpr48806.2021.9412601","mag":"3005829072"},"language":"en","primary_location":{"id":"doi:10.1109/icpr48806.2021.9412601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","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/A5021531256","display_name":"Firas Jarboui","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Firas Jarboui","raw_affiliation_strings":["ANEO - Paris, ENS Paris saclay, Centre BORELLI, Paris","CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)"],"affiliations":[{"raw_affiliation_string":"ANEO - Paris, ENS Paris saclay, Centre BORELLI, Paris","institution_ids":["https://openalex.org/I277688954"]},{"raw_affiliation_string":"CB - CB - Centre Borelli - UMR 9010 (Campus ENS Paris-Saclay\r\n4 Avenue des Sciences,\r\n91190 Gif-sur-Yvette - France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067550667","display_name":"Vianney Perchet","orcid":"https://orcid.org/0000-0002-9333-264X"},"institutions":[{"id":"https://openalex.org/I4210161401","display_name":"Criteo (France)","ror":"https://ror.org/04vyg0r47","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210161401"]},{"id":"https://openalex.org/I4210097629","display_name":"\u00c9cole Nationale d'Administration","ror":"https://ror.org/00x4mq261","country_code":"SN","type":"education","lineage":["https://openalex.org/I4210097629"]}],"countries":["FR","SN"],"is_corresponding":false,"raw_author_name":"Vianney Perchet","raw_affiliation_strings":["CREST, Ensae, Criteo AI Lab, Paris","ENSAE - Ecole Nationale de la Statistique et de l'Analyse Economique (ENSAE-S\u00e9n\u00e9gal Libert\u00e9 VI extension - VDN, N\u00b0 26 BP 45512- Dakar Fann - Senegal)"],"affiliations":[{"raw_affiliation_string":"CREST, Ensae, Criteo AI Lab, Paris","institution_ids":["https://openalex.org/I4210161401"]},{"raw_affiliation_string":"ENSAE - Ecole Nationale de la Statistique et de l'Analyse Economique (ENSAE-S\u00e9n\u00e9gal Libert\u00e9 VI extension - VDN, N\u00b0 26 BP 45512- Dakar Fann - Senegal)","institution_ids":["https://openalex.org/I4210097629"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021531256"],"corresponding_institution_ids":["https://openalex.org/I277688954"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00456145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"6786","last_page":"6793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10328","display_name":"Supply Chain and Inventory Management","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9778000116348267,"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":0.8284938335418701},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8129476308822632},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7649459838867188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.751117467880249},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7372376322746277},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.7247142791748047},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6516199111938477},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5992116928100586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5801497101783752},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5239891409873962},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.47736454010009766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46263259649276733},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4441510736942291},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41707926988601685},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.30305016040802},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1622772216796875},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07578733563423157},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07576212286949158}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8284938335418701},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8129476308822632},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7649459838867188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.751117467880249},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7372376322746277},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.7247142791748047},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6516199111938477},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5992116928100586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5801497101783752},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5239891409873962},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.47736454010009766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46263259649276733},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4441510736942291},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41707926988601685},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30305016040802},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1622772216796875},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07578733563423157},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07576212286949158},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icpr48806.2021.9412601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr48806.2021.9412601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04552027v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04552027","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 25th International Conference on Pattern Recognition (ICPR), Jan 2021, Milan, Italy. pp.6786-6793, ⟨10.1109/ICPR48806.2021.9412601⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W190675879","https://openalex.org/W297984285","https://openalex.org/W1502680304","https://openalex.org/W1515851193","https://openalex.org/W1562936359","https://openalex.org/W1614298861","https://openalex.org/W1757796397","https://openalex.org/W1971955426","https://openalex.org/W2055921164","https://openalex.org/W2064675550","https://openalex.org/W2082099352","https://openalex.org/W2096533821","https://openalex.org/W2096733369","https://openalex.org/W2106053110","https://openalex.org/W2121092017","https://openalex.org/W2133180954","https://openalex.org/W2145339207","https://openalex.org/W2157331557","https://openalex.org/W2161160262","https://openalex.org/W2169743339","https://openalex.org/W2173248099","https://openalex.org/W2347169517","https://openalex.org/W2598634450","https://openalex.org/W2601322194","https://openalex.org/W2607713949","https://openalex.org/W2766736793","https://openalex.org/W2808386811","https://openalex.org/W2914941842","https://openalex.org/W2923504512","https://openalex.org/W2947638559","https://openalex.org/W2950577311","https://openalex.org/W2951585248","https://openalex.org/W2962938178","https://openalex.org/W2963026686","https://openalex.org/W2963094133","https://openalex.org/W2963864421","https://openalex.org/W2964001908","https://openalex.org/W3099206234","https://openalex.org/W4297795006","https://openalex.org/W4298857966","https://openalex.org/W4300799055","https://openalex.org/W6607768588","https://openalex.org/W6610758747","https://openalex.org/W6633322926","https://openalex.org/W6674304311","https://openalex.org/W6677939520","https://openalex.org/W6735944222","https://openalex.org/W6740801417","https://openalex.org/W6752155926","https://openalex.org/W6759440498","https://openalex.org/W6762868464"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2386410636","https://openalex.org/W3038962357"],"abstract_inverted_index":{"Expanding":[0],"Non":[1],"Markovian":[2],"Reward":[3],"Decision":[4,9],"Processes":[5,10],"(NMRDP)":[6],"into":[7,39],"Markov":[8],"(MDP)":[11],"enables":[12],"the":[13,18,42,46,55,61,77,81,103,113],"use":[14],"of":[15,17,45,54,65,86,102,112],"state":[16],"art":[19],"Reinforcement":[20],"Learning":[21],"(RL)":[22],"techniques":[23],"to":[24,33,108],"identify":[25],"optimal":[26],"policies.":[27],"In":[28],"this":[29],"paper":[30],"an":[31],"approach":[32],"exploring":[34],"NMRDPs":[35],"and":[36,67],"expanding":[37],"them":[38],"MDPs,":[40],"without":[41],"prior":[43],"knowledge":[44],"reward":[47,56],"structure,":[48],"is":[49,58,88,96,106],"proposed.":[50],"The":[51],"non":[52],"Markovianity":[53],"function":[57],"disentangled":[59],"under":[60,115],"assumption":[62],"that":[63],"sets":[64],"similar":[66],"dissimilar":[68],"trajectory":[69],"batches":[70,95],"can":[71],"be":[72],"sampled.":[73],"More":[74],"precisely,":[75],"within":[76],"same":[78],"batch,":[79],"measuring":[80],"similarity":[82],"between":[83],"any":[84],"couple":[85],"trajectories":[87,92,114],"permitted,":[89],"although":[90],"comparing":[91],"from":[93],"different":[94],"not":[97],"possible.":[98],"A":[99],"modified":[100],"version":[101],"triplet":[104],"loss":[105],"optimised":[107],"construct":[109],"a":[110],"representation":[111],"which":[116],"rewards":[117],"become":[118],"Markovian.":[119]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}