{"id":"https://openalex.org/W4416251343","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227725","title":"Navigation With QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","display_name":"Navigation With QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251343","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227725"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5027352146","display_name":"A. Canesse","orcid":"https://orcid.org/0000-0002-9227-5217"},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]},{"id":"https://openalex.org/I4210120985","display_name":"Institut d'Histoire des Repr\u00e9sentations et des Id\u00e9es dans les Modernit\u00e9s","ror":"https://ror.org/02wmc6m46","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I198244214","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210120985","https://openalex.org/I4405259976","https://openalex.org/I874609350"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alexi Canesse","raw_affiliation_strings":["ENS Lyon"],"affiliations":[{"raw_affiliation_string":"ENS Lyon","institution_ids":["https://openalex.org/I4210120985","https://openalex.org/I113428412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114654624","display_name":"Mathieu Petitbois","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]},{"id":"https://openalex.org/I4210145683","display_name":"Forge (United Kingdom)","ror":"https://ror.org/0427ccd45","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210145683"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Mathieu Petitbois","raw_affiliation_strings":["Ubisoft La Forge"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge","institution_ids":["https://openalex.org/I4210104072","https://openalex.org/I4210145683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027101473","display_name":"Ludovic Denoyer","orcid":null},"institutions":[{"id":"https://openalex.org/I206578319","display_name":"Southern Company (United States)","ror":"https://ror.org/02r0g0093","country_code":"US","type":"company","lineage":["https://openalex.org/I206578319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ludovic Denoyer","raw_affiliation_strings":["H Company"],"affiliations":[{"raw_affiliation_string":"H Company","institution_ids":["https://openalex.org/I206578319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031635996","display_name":"Sylvain Lamprier","orcid":"https://orcid.org/0000-0002-2508-922X"},"institutions":[{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sylvain Lamprier","raw_affiliation_strings":["University of Angers"],"affiliations":[{"raw_affiliation_string":"University of Angers","institution_ids":["https://openalex.org/I49451733"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006159402","display_name":"R\u00e9my Portelas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104072","display_name":"Ubisoft (Canada)","ror":"https://ror.org/01hmp5p66","country_code":"CA","type":"company","lineage":["https://openalex.org/I4210104072"]},{"id":"https://openalex.org/I4210145683","display_name":"Forge (United Kingdom)","ror":"https://ror.org/0427ccd45","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210145683"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"R\u00e9my Portelas","raw_affiliation_strings":["Ubisoft La Forge"],"affiliations":[{"raw_affiliation_string":"Ubisoft La Forge","institution_ids":["https://openalex.org/I4210104072","https://openalex.org/I4210145683"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027352146"],"corresponding_institution_ids":["https://openalex.org/I113428412","https://openalex.org/I4210120985"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19464411,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.39570000767707825,"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":0.39570000767707825,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3310000002384186,"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"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.10379999876022339,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6557999849319458},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.46970000863075256},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.4609000086784363},{"id":"https://openalex.org/keywords/image-stitching","display_name":"Image stitching","score":0.45590001344680786},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.44110000133514404},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.42809998989105225},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.3862999975681305},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.365200012922287},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.33889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128999829292297},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6557999849319458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5947999954223633},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.44110000133514404},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33889999985694885},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.31700000166893005},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.31610000133514404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3068999946117401},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2107726111","https://openalex.org/W2109910161","https://openalex.org/W2612112834","https://openalex.org/W3187808158","https://openalex.org/W4281550413","https://openalex.org/W4312282783","https://openalex.org/W4360584316","https://openalex.org/W4382202964","https://openalex.org/W4385245566","https://openalex.org/W4385764328","https://openalex.org/W4386072289","https://openalex.org/W4389667622","https://openalex.org/W4400111461"],"related_works":[],"abstract_inverted_index":{"Offline":[0,30],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,76,82,101],"powerful":[8],"alternative":[9],"to":[10,38,44,89,112],"imitation":[11],"learning":[12],"for":[13],"behavior":[14],"modeling":[15],"in":[16,20,46,121,145,154],"various":[17],"domains,":[18],"particularly":[19],"complex":[21,155],"long":[22,91],"range":[23],"navigation":[24,93,157],"tasks.":[25,94],"An":[26],"existing":[27],"challenge":[28],"with":[29,142],"RL":[31,60],"is":[32,110],"the":[33,55,86,98],"signal-to-noise":[34],"ratio,":[35],"i.e.":[36],"how":[37],"mitigate":[39],"incorrect":[40],"policy":[41,105],"updates":[42],"due":[43],"errors":[45],"value":[47,134],"estimates.":[48,136],"Towards":[49],"this,":[50],"multiple":[51],"works":[52],"have":[53],"demonstrated":[54],"advantage":[56],"of":[57,85,100],"hierarchical":[58,78],"offline":[59,146],"methods,":[61],"which":[62,109],"decouples":[63],"high-level":[64],"path":[65,69],"planning":[66,122],"from":[67],"low-level":[68,104],"following.":[70],"In":[71],"this":[72,139],"work,":[73],"we":[74],"present":[75],"novel":[77],"transformer-based":[79,140],"approach":[80,150],"leveraging":[81],"learned":[83],"quantizer":[84],"state":[87],"space":[88],"tackle":[90],"horizon":[92],"This":[95],"quantization":[96],"enables":[97,123],"training":[99],"simpler":[102],"zone-conditioned":[103],"and":[106],"simplifies":[107],"planning,":[108],"reduced":[111],"discrete":[113],"autoregressive":[114],"prediction.":[115],"Among":[116],"other":[117],"benefits,":[118],"zone-level":[119],"reasoning":[120],"explicit":[124],"trajectory":[125],"stitching":[126,130],"rather":[127],"than":[128],"implicit":[129],"based":[131],"on":[132],"noisy":[133],"function":[135],"By":[137],"combining":[138],"planner":[141],"recent":[143],"advancements":[144],"RL,":[147],"our":[148],"proposed":[149],"achieves":[151],"state-of-the-art":[152],"results":[153],"long-distance":[156],"environments.":[158]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}