{"id":"https://openalex.org/W4416545271","doi":"https://doi.org/10.1109/iccv51701.2025.00252","title":"ULTHO: Ultra-Lightweight Yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning","display_name":"ULTHO: Ultra-Lightweight Yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416545271","doi":"https://doi.org/10.1109/iccv51701.2025.00252"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.06101","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110921988","display_name":"Mingqi Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mingqi Yuan","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Computing,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Computing,Hong Kong SAR,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374494","display_name":"Bo Li","orcid":"https://orcid.org/0000-0003-0721-0601"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Computing,Hong Kong SAR,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Computing,Hong Kong SAR,China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100641352","display_name":"Xin Jin","orcid":"https://orcid.org/0000-0003-3873-1653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049963367","display_name":"Wenjun Zeng","orcid":"https://orcid.org/0000-0003-2531-3137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjun Zeng","raw_affiliation_strings":["Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ningbo Institute of Digital Twin, Eastern Institute of Technology,Ningbo,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17124333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2620","last_page":"2630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.6873000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6873000264167786,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.09719999879598618,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.039799999445676804,"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/hyperparameter","display_name":"Hyperparameter","score":0.8105999827384949},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.7215999960899353},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6604999899864197},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4503999948501587},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.45010000467300415},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.42590001225471497},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8105999827384949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415000200271606},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.7215999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7135999798774719},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6873999834060669},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6604999899864197},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.42590001225471497},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.06101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06101","pdf_url":"https://arxiv.org/pdf/2503.06101","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.06101","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.06101","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.06101","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.06101","pdf_url":"https://arxiv.org/pdf/2503.06101","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3527258163","display_name":null,"funder_award_id":"62302246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3773096341","display_name":null,"funder_award_id":"15224823","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hyperparameter":[0],"optimization":[1],"(HPO)":[2],"is":[3,30],"a":[4,73,105,123,155],"billion-dollar":[5],"problem":[6],"in":[7,25,92],"machine":[8],"learning,":[9],"which":[10,70],"significantly":[11],"impacts":[12],"the":[13,60,101,130,148,160],"training":[14,55],"efficiency":[15],"and":[16,22,38,67,112,125,142,164],"model":[17],"performance.":[18],"However,":[19,63],"achieving":[20],"efficient":[21],"robust":[23],"HPO":[24,51,91,102],"deep":[26,93],"reinforcement":[27],"learning":[28],"(RL)":[29],"consistently":[31],"challenging":[32],"due":[33],"to":[34,48,59,116,128,159],"its":[35],"high":[36],"non-stationarity":[37],"computational":[39],"cost.":[40],"To":[41],"tackle":[42],"this":[43,79],"problem,":[44],"existing":[45],"approaches":[46],"attempt":[47],"adapt":[49],"common":[50],"techniques":[52],"(e.g.,":[53],"population-based":[54],"or":[56],"Bayesian":[57],"optimization)":[58],"RL":[61,94,166],"scenario.":[62],"they":[64],"remain":[65],"sample-inefficient":[66],"computationally":[68],"expensive,":[69],"cannot":[71],"facilitate":[72],"wide":[74],"range":[75],"of":[76,162],"applications.":[77],"In":[78],"paper,":[80],"we":[81,99],"propose":[82],"ULTHO,":[83],"an":[84],"ultra-lightweight":[85],"yet":[86],"powerful":[87],"framework":[88],"for":[89],"fast":[90],"within":[95],"single":[96],"runs.":[97],"Specifically,":[98],"formulate":[100],"process":[103],"as":[104],"multi-armed":[106],"bandit":[107],"with":[108,154],"clustered":[109],"arms":[110],"(MABC)":[111],"link":[113],"it":[114],"directly":[115],"long-term":[117],"return":[118],"optimization.":[119],"ULTHO":[120,135,149],"also":[121],"provides":[122],"quantified":[124],"statistical":[126],"perspective":[127],"filter":[129],"HPs":[131],"efficiently.":[132],"We":[133],"test":[134],"on":[136],"benchmarks":[137],"including":[138],"ALE,":[139],"Procgen,":[140],"MiniGrid,":[141],"PyBullet.":[143],"Extensive":[144],"experiments":[145],"demonstrate":[146],"that":[147],"can":[150],"achieve":[151],"superior":[152],"performance":[153],"simple":[156],"architecture,":[157],"contributing":[158],"development":[161],"advanced":[163],"automated":[165],"systems.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}