{"id":"https://openalex.org/W3153709347","doi":"https://doi.org/10.1007/s42979-021-00642-4","title":"Gaussian Based Non-linear Function Approximation for Reinforcement Learning","display_name":"Gaussian Based Non-linear Function Approximation for Reinforcement Learning","publication_year":2021,"publication_date":"2021-04-20","ids":{"openalex":"https://openalex.org/W3153709347","doi":"https://doi.org/10.1007/s42979-021-00642-4","mag":"3153709347"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-021-00642-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-021-00642-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-021-00642-4.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","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/s42979-021-00642-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037285328","display_name":"Abbas Haider","orcid":"https://orcid.org/0000-0003-1802-3086"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Abbas Haider","raw_affiliation_strings":["School of Computing, Ulster University, Jordanstown, Northern Ireland, UK"],"raw_orcid":"https://orcid.org/0000-0003-1802-3086","affiliations":[{"raw_affiliation_string":"School of Computing, Ulster University, Jordanstown, Northern Ireland, UK","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048737234","display_name":"Glenn Hawe","orcid":"https://orcid.org/0000-0002-0590-8494"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Glenn Hawe","raw_affiliation_strings":["School of Computing, Ulster University, Jordanstown, Northern Ireland, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Ulster University, Jordanstown, Northern Ireland, UK","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460917","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0003-2633-6015"},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["School of Computing, Ulster University, Jordanstown, Northern Ireland, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Ulster University, Jordanstown, Northern Ireland, UK","institution_ids":["https://openalex.org/I138801177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105285988","display_name":"Bryan Scotney","orcid":null},"institutions":[{"id":"https://openalex.org/I138801177","display_name":"University of Ulster","ror":"https://ror.org/01yp9g959","country_code":"GB","type":"education","lineage":["https://openalex.org/I138801177"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bryan Scotney","raw_affiliation_strings":["School of Computing, Ulster University, Jordanstown, Northern Ireland, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Ulster University, Jordanstown, Northern Ireland, UK","institution_ids":["https://openalex.org/I138801177"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5037285328"],"corresponding_institution_ids":["https://openalex.org/I138801177"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":0.6824,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74442334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9976000189781189,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6116101145744324},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5591814517974854},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5340273380279541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4634871780872345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45305317640304565},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4428200125694275},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.42475658655166626},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4137040674686432},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3732697069644928},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1329423487186432},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.08132687211036682}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6116101145744324},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5591814517974854},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5340273380279541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4634871780872345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45305317640304565},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4428200125694275},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.42475658655166626},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4137040674686432},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3732697069644928},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1329423487186432},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.08132687211036682},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s42979-021-00642-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-021-00642-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-021-00642-4.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/ede9cde2-9057-41df-8ee2-3a56046a9ae2","is_oa":true,"landing_page_url":"https://pure.ulster.ac.uk/en/publications/ede9cde2-9057-41df-8ee2-3a56046a9ae2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402454","display_name":"Ulster University Research Portal (Ulster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I138801177","host_organization_name":"University of Ulster","host_organization_lineage":["https://openalex.org/I138801177"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Haider, A, Hawe, G, Wang, H & Scotney, B 2021, 'Gaussian Based Non-linear Function Approximation for Reinforcement Learning', SN Computer Science, vol. 2, no. 3, 223, pp. 223. https://doi.org/10.1007/s42979-021-00642-4","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s42979-021-00642-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s42979-021-00642-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s42979-021-00642-4.pdf","source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["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":"SN Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3153709347.pdf","grobid_xml":"https://content.openalex.org/works/W3153709347.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W16011919","https://openalex.org/W166862392","https://openalex.org/W599808240","https://openalex.org/W1552830313","https://openalex.org/W1557517019","https://openalex.org/W1576452626","https://openalex.org/W1757796397","https://openalex.org/W2100677568","https://openalex.org/W2101786389","https://openalex.org/W2141562047","https://openalex.org/W2143908786","https://openalex.org/W2145756561","https://openalex.org/W2162288466","https://openalex.org/W2173564293","https://openalex.org/W2596758708","https://openalex.org/W2746553466","https://openalex.org/W2796037385","https://openalex.org/W2796688914","https://openalex.org/W2804606950","https://openalex.org/W2902334345","https://openalex.org/W2907503094","https://openalex.org/W2911283634","https://openalex.org/W2929242575","https://openalex.org/W2952343792","https://openalex.org/W2963477884","https://openalex.org/W2966944379","https://openalex.org/W2997767088","https://openalex.org/W3011120880","https://openalex.org/W3139377883","https://openalex.org/W4252673275","https://openalex.org/W4285719527","https://openalex.org/W4307347247","https://openalex.org/W6634528131","https://openalex.org/W6689723076"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1,67],"learning":[2],"(RL)":[3],"problems":[4,38,144],"with":[5,93,172],"continuous":[6],"states":[7,49],"and":[8,22,52,64,161,175,194],"discrete":[9],"actions":[10,51],"(CSDA)":[11],"can":[12,53],"be":[13,54],"found":[14],"in":[15,66,90,103],"classic":[16],"examples":[17],"such":[18,31,60,84],"as":[19,25,27,32,61,85],"Cart":[20],"Pole":[21],"Puck":[23,147],"World,":[24,148],"well":[26],"real":[28],"world":[29],"applications":[30],"Market":[33,149],"Making.":[34],"Solutions":[35],"to":[36,50,78,109,128],"CSDA":[37,129,142],"typically":[39],"involve":[40],"a":[41,124],"function":[42,136],"approximation":[43,137],"(FA)":[44],"of":[45,154],"the":[46,152,167],"mapping":[47],"from":[48,73],"linear":[55,173,187],"or":[56],"nonlinear.":[57],"Linear":[58],"FAs":[59,83,174,188,199],"tile-coding":[62,160],"(Sutton":[63],"Barto":[65],"learning,":[68,96],"2nd":[69],"ed,":[70],"2009)":[71],"suffer":[72],"state":[74,79,106,168],"information":[75,169],"loss":[76,170],"due":[77,108],"discretization,":[80],"whilst":[81],"non-linear":[82,135],"DQN":[86],"(Mnih":[87],"et":[88],"al.":[89],"Playing":[91],"atari":[92],"deep":[94],"reinforcement":[95],"https://arxiv.org/abs/1312.5602":[97],",":[98],"2013)":[99],"are":[100],"practically":[101],"infeasible":[102],"infinitely":[104],"large":[105],"spaces":[107],"their":[110],"cubic":[111],"time":[112],"complexity":[113],"(":[114,181,183,189,200],"$$O(n^3)$$":[115,201],"<mml:math":[116,191,202],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mi>O</mml:mi><mml:mo>(</mml:mo><mml:msup><mml:mi>n</mml:mi><mml:mn>3</mml:mn></mml:msup><mml:mo>)</mml:mo></mml:mrow></mml:math>":[117,203],").":[118,204],"In":[119,163],"this":[120],"paper,":[121],"we":[122],"propose":[123],"novel,":[125],"general":[126],"solution":[127],"problems,":[130],"called":[131],"Gaussian":[132],"distribution":[133],"based":[134,197],"(GBNLFA).":[138],"Experimentation":[139],"on":[140],"three":[141],"RL":[143],"(Cart":[145],"Pole,":[146],"Marking)":[150],"demonstrates":[151],"superiority":[153],"GBNLFA":[155,165],"over":[156],"state-of-the-art":[157],"FAs,":[158],"namely":[159],"DQN.":[162],"particular,":[164],"resolves":[166],"problem":[171],"provides":[176],"an":[177],"asymptotically":[178],"faster":[179],"algorithm":[180],"O":[182],"n":[184],"))":[185],"than":[186],"$$O(n^2)$$":[190],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mrow><mml:mi>O</mml:mi><mml:mo>(</mml:mo><mml:msup><mml:mi>n</mml:mi><mml:mn>2</mml:mn></mml:msup><mml:mo>)</mml:mo></mml:mrow></mml:math>":[192],")":[193],"neural":[195],"network":[196],"nonlinear":[198]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}