{"id":"https://openalex.org/W4415933808","doi":"https://doi.org/10.1109/tnnls.2025.3626536","title":"ORAL: Adaptive Gap Increasing for Advantage Learning via Occam\u2019s Razor Principle","display_name":"ORAL: Adaptive Gap Increasing for Advantage Learning via Occam\u2019s Razor Principle","publication_year":2025,"publication_date":"2025-11-05","ids":{"openalex":"https://openalex.org/W4415933808","doi":"https://doi.org/10.1109/tnnls.2025.3626536","pmid":"https://pubmed.ncbi.nlm.nih.gov/41191465"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3626536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3626536","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100443035","display_name":"Zhe Zhang","orcid":"https://orcid.org/0000-0002-7960-5533"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["College of Information Science and Technology, Jinan University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7960-5533","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001366934","display_name":"Yongle Zhou","orcid":"https://orcid.org/0009-0007-4398-1418"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongle Zhou","raw_affiliation_strings":["College of Information Science and Technology, Jinan University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0007-4398-1418","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600268","display_name":"Yuyang Long","orcid":"https://orcid.org/0000-0001-5588-2213"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuyang Long","raw_affiliation_strings":["College of Information Science and Technology, Jinan University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706302","display_name":"Jia Zhang","orcid":"https://orcid.org/0000-0002-6079-2818"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Zhang","raw_affiliation_strings":["College of Information Science and Technology, Jinan University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6079-2818","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041234756","display_name":"Juanjuan Weng","orcid":"https://orcid.org/0000-0003-0825-2272"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanjuan Weng","raw_affiliation_strings":["College of Information Science and Technology, Jinan University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081827896","display_name":"Zhetao Li","orcid":"https://orcid.org/0000-0002-7804-0286"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhetao Li","raw_affiliation_strings":["College of Information Science and Technology, Jinan University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7804-0286","affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016091831","display_name":"Yaozhong Gan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaozhong Gan","raw_affiliation_strings":["Qiyuan Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qiyuan Lab, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004478562","display_name":"Xiaoyang Tan","orcid":"https://orcid.org/0000-0002-2683-8667"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Tan","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2683-8667","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100443035"],"corresponding_institution_ids":["https://openalex.org/I159948400"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16497669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"4","first_page":"1904","last_page":"1918"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9057999849319458,"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":0.9057999849319458,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.018300000578165054,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.013799999840557575,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7149999737739563},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.6194999814033508},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5900999903678894},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4666000008583069},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.45680001378059387},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.43689998984336853},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4153999984264374},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4099999964237213}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7149999737739563},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.6194999814033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5906999707221985},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5900999903678894},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48910000920295715},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4153999984264374},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.375},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3447999954223633},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2574999928474426},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3626536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3626536","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:41191465","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41191465","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2173691295","display_name":null,"funder_award_id":"21625348","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4108615628","display_name":null,"funder_award_id":"21625110","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6380748910","display_name":null,"funder_award_id":"62506191","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7215590708","display_name":null,"funder_award_id":"62476128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Benefiting":[0],"from":[1],"the":[2,6,12,24,29,50,86,92,101,110,117,135,173,183],"gap":[3,103,184],"increasing":[4,91,185],"between":[5],"optimal":[7,118],"action":[8,46,93,102],"and":[9,44,84,138,163],"its":[10,42,193],"competitors,":[11],"advantage":[13],"learning":[14,35],"(AL)":[15],"operator":[16,32],"is":[17],"more":[18,149,166],"robust":[19],"to":[20,59,116,133,165,181],"estimation":[21],"errors":[22],"in":[23,33],"approximated":[25],"$Q$":[26,114],"-functions":[27],"than":[28],"Bellman":[30],"optimality":[31],"reinforcement":[34],"(RL).":[36],"However,":[37],"our":[38,96,153,176],"analysis":[39,171],"reveals":[40],"that":[41],"robustness":[43],"larger":[45],"gaps":[47],"come":[48],"at":[49,147],"cost":[51],"of":[52,62,112,126,144,175],"a":[53,71,123,129,141],"worse":[54],"performance":[55,197],"loss":[56],"bound,":[57],"leading":[58],"slower":[60],"convergence":[61],"value":[63],"functions.":[64],"To":[65],"address":[66],"this":[67],"issue,":[68],"we":[69],"present":[70],"novel":[72],"method,":[73],"named":[74],"Occam's":[75,81],"Razor-based":[76],"AL":[77],"(ORAL),":[78],"which":[79],"follows":[80],"Razor":[82],"principle":[83],"takes":[85],"necessity":[87],"into":[88,159],"consideration":[89],"when":[90],"gap.":[94],"Specifically,":[95],"ORAL":[97,145],"can":[98,155],"adaptively":[99],"increase":[100],"for":[104],"different":[105],"state-action":[106],"pairs,":[107],"depending":[108],"on":[109],"proximity":[111],"their":[113,179],"values":[115],"ones.":[119],"We":[120],"first":[121],"propose":[122],"naive":[124],"implementation":[125],"ORAL,":[127],"employing":[128],"nonsmooth":[130],"clipping":[131],"function":[132],"realize":[134],"above":[136],"idea,":[137],"then":[139],"introduce":[140],"smooth":[142],"version":[143],"aimed":[146],"achieving":[148],"stable":[150],"learning.":[151],"Furthermore,":[152],"methods":[154],"be":[156],"easily":[157],"plugged":[158],"other":[160],"AL-based":[161],"operators":[162],"extended":[164],"complex":[167],"continuous-control":[168],"tasks.":[169],"Theoretical":[170],"supports":[172],"feasibility":[174],"approaches,":[177],"demonstrating":[178],"ability":[180],"balance":[182],"with":[186],"fast":[187],"convergence.":[188],"Empirical":[189],"results":[190],"further":[191],"validate":[192],"effectiveness,":[194],"showing":[195],"significant":[196],"improvements":[198],"across":[199],"multiple":[200],"benchmarks.":[201]},"counts_by_year":[],"updated_date":"2026-04-07T06:01:17.266235","created_date":"2025-11-05T00:00:00"}