{"id":"https://openalex.org/W4416252423","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227331","title":"Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning","display_name":"Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252423","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227331"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227331","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":"conference-paper","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/A5034825235","display_name":"Guoqing Ma","orcid":"https://orcid.org/0000-0002-5429-9082"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Ma","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385429","display_name":"Yuhan Zhang","orcid":"https://orcid.org/0009-0001-0686-3865"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhan Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059136175","display_name":"Yuming Dai","orcid":"https://orcid.org/0000-0003-3777-5646"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Dai","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026377137","display_name":"Guangfu Hao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangfu Hao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912546","display_name":"Yang Chen","orcid":"https://orcid.org/0000-0002-7363-1108"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100759691","display_name":"Shan Yu","orcid":"https://orcid.org/0000-0002-9008-6658"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8991000056266785,"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":0.8991000056266785,"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":0.01209999993443489,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.00570000009611249,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8414000272750854},{"id":"https://openalex.org/keywords/orthogonalization","display_name":"Orthogonalization","score":0.6610999703407288},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.635699987411499},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6355000138282776},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6010000109672546},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4408000111579895},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8414000272750854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700000166893005},{"id":"https://openalex.org/C47559304","wikidata":"https://www.wikidata.org/wiki/Q1702189","display_name":"Orthogonalization","level":2,"score":0.6610999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6419000029563904},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.635699987411499},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6355000138282776},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6010000109672546},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43059998750686646},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31220000982284546},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227331","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227331","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1587845729","https://openalex.org/W2073849744","https://openalex.org/W2141559645","https://openalex.org/W2169743339","https://openalex.org/W2473930607","https://openalex.org/W2560647685","https://openalex.org/W2895699061","https://openalex.org/W2902332709","https://openalex.org/W2902907165","https://openalex.org/W2943927637","https://openalex.org/W2951360122","https://openalex.org/W2962707369","https://openalex.org/W2963582482","https://openalex.org/W3008998212","https://openalex.org/W3034867292","https://openalex.org/W3106901158","https://openalex.org/W3117215073","https://openalex.org/W4213377513","https://openalex.org/W4221067122","https://openalex.org/W4252279978","https://openalex.org/W4302010773","https://openalex.org/W4379739787","https://openalex.org/W4386285856","https://openalex.org/W4390191191","https://openalex.org/W4392903172","https://openalex.org/W4393147501","https://openalex.org/W4401415064","https://openalex.org/W4409199977","https://openalex.org/W4410636390","https://openalex.org/W4415566408"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,30,87,102,113],"(RL)":[2],"has":[3],"made":[4],"significant":[5],"advancements,":[6],"achieving":[7],"superhuman":[8],"performance":[9],"in":[10,41,128],"various":[11,141],"tasks.":[12,144],"However,":[13],"RL":[14,76],"agents":[15],"often":[16],"operate":[17],"under":[18],"the":[19,42,59,71,86,111,116],"assumption":[20],"of":[21,44,46,74,124],"environmental":[22],"stationarity,":[23],"which":[24,66],"poses":[25],"a":[26,94],"great":[27],"challenge":[28],"to":[29,49],"efficiency":[31],"since":[32],"many":[33],"environments":[34],"are":[35],"inherently":[36],"non-stationary.":[37],"This":[38],"non-stationarity":[39,80],"results":[40],"requirement":[43],"millions":[45],"iterations,":[47],"leading":[48],"low":[50],"sample":[51],"efficiency.":[52,114],"To":[53],"address":[54],"this":[55],"issue,":[56],"we":[57],"introduce":[58],"Clustering":[60],"Orthogonal":[61],"Weight":[62],"Modified":[63],"(COWM)":[64],"layer,":[65],"can":[67],"be":[68],"integrated":[69],"into":[70],"policy":[72],"network":[73],"any":[75],"algorithm":[77],"and":[78,93,121,126,130,138,143],"mitigate":[79],"effectively.":[81],"The":[82],"COWM":[83,117],"layer":[84],"stabilizes":[85],"process":[88],"by":[89],"employing":[90],"clustering":[91],"techniques":[92],"projection":[95],"matrix.":[96],"Our":[97],"approach":[98],"not":[99],"only":[100],"improves":[101],"speed":[103],"but":[104],"also":[105,135],"reduces":[106],"gradient":[107],"interference,":[108],"thereby":[109],"enhancing":[110],"overall":[112],"Empirically,":[115],"outperforms":[118],"state-of-the-art":[119],"methods":[120],"achieves":[122],"improvements":[123],"9%":[125],"12.6%":[127],"vision-based":[129],"state-based":[131],"DMControl":[132],"benchmark.":[133],"It":[134],"shows":[136],"robustness":[137],"generality":[139],"across":[140],"algorithms":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-14T00:00:00"}