{"id":"https://openalex.org/W4399369995","doi":"https://doi.org/10.1007/s10994-024-06547-6","title":"A framework for training larger networks for deep Reinforcement learning","display_name":"A framework for training larger networks for deep Reinforcement learning","publication_year":2024,"publication_date":"2024-06-05","ids":{"openalex":"https://openalex.org/W4399369995","doi":"https://doi.org/10.1007/s10994-024-06547-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-024-06547-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06547-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06547-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06547-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064968116","display_name":"Kei Ota","orcid":"https://orcid.org/0000-0002-5744-3027"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]},{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kei Ota","raw_affiliation_strings":["Information Technology R &D Center, Mitsubishi Electric Corporation, 5-1-1 Oofuna, Kamakura, Kanagawa, 247-0056, Japan","School of Computing, Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, 152-8550, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5744-3027","affiliations":[{"raw_affiliation_string":"Information Technology R &D Center, Mitsubishi Electric Corporation, 5-1-1 Oofuna, Kamakura, Kanagawa, 247-0056, Japan","institution_ids":["https://openalex.org/I4210133125"]},{"raw_affiliation_string":"School of Computing, Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, 152-8550, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010530960","display_name":"Devesh K. Jha","orcid":"https://orcid.org/0000-0002-7843-9545"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Devesh K. Jha","raw_affiliation_strings":["Mitsubishi Electric Research Labs, 201 Broadway, Cambridge, MA, 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Labs, 201 Broadway, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045505869","display_name":"Asako Kanezaki","orcid":"https://orcid.org/0000-0003-3217-1405"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asako Kanezaki","raw_affiliation_strings":["School of Computing, Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, 152-8550, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Tokyo Institute of Technology, 2-12-1 Ookayama, Meguro-ku, Tokyo, 152-8550, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064968116"],"corresponding_institution_ids":["https://openalex.org/I114531698","https://openalex.org/I4210133125"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":1.2151,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81559174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"113","issue":"9","first_page":"6115","last_page":"6139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9814000129699707,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/overfitting","display_name":"Overfitting","score":0.8774587512016296},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8226565718650818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8021688461303711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7277096509933472},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6091554760932922},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6023341417312622},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6014033555984497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5254408717155457},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5085636377334595}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8774587512016296},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8226565718650818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021688461303711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7277096509933472},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6091554760932922},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6023341417312622},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6014033555984497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5254408717155457},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5085636377334595},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-024-06547-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06547-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06547-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-024-06547-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-024-06547-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-024-06547-6.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399369995.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1836465849","https://openalex.org/W2108598243","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2551887912","https://openalex.org/W2558580397","https://openalex.org/W2563830277","https://openalex.org/W2570734388","https://openalex.org/W2746553466","https://openalex.org/W2754517384","https://openalex.org/W2761873684","https://openalex.org/W2781726626","https://openalex.org/W2787666871","https://openalex.org/W2787938642","https://openalex.org/W2896457183","https://openalex.org/W2902098903","https://openalex.org/W2908064123","https://openalex.org/W2912260645","https://openalex.org/W2944828972","https://openalex.org/W2946948417","https://openalex.org/W2950220847","https://openalex.org/W2963446712","https://openalex.org/W2964137095","https://openalex.org/W2990138404","https://openalex.org/W3005680577","https://openalex.org/W3035524453","https://openalex.org/W3035700320","https://openalex.org/W3036982689","https://openalex.org/W3096471977","https://openalex.org/W3169291081","https://openalex.org/W4221141793","https://openalex.org/W4312909062","https://openalex.org/W4385430679","https://openalex.org/W6687681856","https://openalex.org/W6736786397","https://openalex.org/W6740801417","https://openalex.org/W6743923790","https://openalex.org/W6746023985","https://openalex.org/W6747381837","https://openalex.org/W6754184789","https://openalex.org/W6760755450","https://openalex.org/W6769739676","https://openalex.org/W6778883912","https://openalex.org/W6780404908","https://openalex.org/W6839626769"],"related_works":["https://openalex.org/W3099765033","https://openalex.org/W2786764570","https://openalex.org/W4309960894","https://openalex.org/W2728804654","https://openalex.org/W4377865163","https://openalex.org/W3193857078","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"success":[2],"of":[3,20,29,39,50,79,100,126,140,180,188],"deep":[4,22,51,80,104],"learning":[5,53,136],"in":[6,167],"computer":[7],"vision":[8],"and":[9,96,142,184],"natural":[10],"language":[11],"processing":[12],"communities":[13],"can":[14,32,160],"be":[15,34],"attributed":[16],"to":[17,62,74,94,148,176],"the":[18,48,77,98,138,178,181,189],"training":[19,49,78,99,139,146],"very":[21,162],"neural":[23],"networks":[24,58,102,129,164],"with":[25,36,130],"millions":[26],"or":[27],"billions":[28],"parameters,":[30],"which":[31],"then":[33],"trained":[35],"massive":[37],"amounts":[38],"data.":[40],"However,":[41],"a":[42,121,144],"similar":[43],"trend":[44],"has":[45,67],"largely":[46],"eluded":[47],"reinforcement":[52],"(RL)":[54],"algorithms":[55,203],"where":[56],"larger":[57,85,101],"do":[59],"not":[60,115],"lead":[61],"performance":[63,169,192],"improvement.":[64],"Previous":[65],"work":[66],"shown":[68],"that":[69,109,124,158,165,196],"this":[70,88,153],"is":[71],"mostly":[72],"due":[73],"instability":[75],"during":[76],"RL":[81],"agents":[82],"when":[83],"using":[84],"networks.":[86],"In":[87],"paper,":[89],"we":[90,119,156,159],"make":[91],"an":[92],"attempt":[93],"understand":[95],"address":[97],"for":[103,191],"RL.":[105],"We":[106,171,194],"first":[107],"show":[108,157,195],"naively":[110],"increasing":[111],"network":[112],"capacity":[113],"does":[114],"improve":[116],"performance.":[117],"Then,":[118],"propose":[120],"novel":[122],"method":[123,147,183,199],"consists":[125],"(1)":[127],"wider":[128],"DenseNet":[131],"connection,":[132],"(2)":[133],"decoupling":[134],"representation":[135],"from":[137],"RL,":[141],"(3)":[143],"distributed":[145],"mitigate":[149],"overfitting":[150],"problems.":[151],"Using":[152],"three-fold":[154],"technique,":[155],"train":[161],"large":[163],"result":[166],"significant":[168],"gains.":[170],"present":[172],"several":[173,205],"ablation":[174],"studies":[175],"demonstrate":[177],"efficacy":[179],"proposed":[182,198],"some":[185],"intuitive":[186],"understanding":[187],"reasons":[190],"gain.":[193],"our":[197],"outperforms":[200],"other":[201],"baseline":[202],"on":[204],"challenging":[206],"locomotion":[207],"tasks.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}