{"id":"https://openalex.org/W7224997138","doi":"https://doi.org/10.1007/s44163-026-02533-0","title":"Solving elliptic partial differential equation based on deep reinforcement learning","display_name":"Solving elliptic partial differential equation based on deep reinforcement learning","publication_year":2026,"publication_date":"2026-10-31","ids":{"openalex":"https://openalex.org/W7224997138","doi":"https://doi.org/10.1007/s44163-026-02533-0"},"language":"en","primary_location":{"id":"doi:10.1007/s44163-026-02533-0","doi":"https://doi.org/10.1007/s44163-026-02533-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-02533-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02533-0.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","oarl"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02533-0.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160239960","display_name":"Mengyao Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405279813","display_name":"Luoyang Vocational College of Culture and Tourism","ror":"https://ror.org/021tnp153","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405279813"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mengyao Li","raw_affiliation_strings":["Department of General Basic Education, Luoyang Vocational College of Culture and Tourism, Luoyang, 471000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of General Basic Education, Luoyang Vocational College of Culture and Tourism, Luoyang, 471000, China","institution_ids":["https://openalex.org/I4405279813"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5160239960"],"corresponding_institution_ids":["https://openalex.org/I4405279813"],"apc_list":{"value":1590,"currency":"USD","value_usd":1590},"apc_paid":{"value":1590,"currency":"USD","value_usd":1590},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.8347842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.0006000000284984708,"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/elliptic-equations","display_name":"elliptic equations","score":0.996999979019165},{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.9440000057220459},{"id":"https://openalex.org/keywords/deep-q-network","display_name":"deep Q-network","score":0.9559999704360962},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7799999713897705},{"id":"https://openalex.org/keywords/pde-solvers","display_name":"PDE solvers","score":0.7369999885559082},{"id":"https://openalex.org/keywords/poisson-equation","display_name":"Poisson equation","score":0.7519999742507935},{"id":"https://openalex.org/keywords/helmholtz-equation","display_name":"Helmholtz equation","score":1.0},{"id":"https://openalex.org/keywords/anisotropic-diffusion","display_name":"anisotropic diffusion","score":0.9440000057220459},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.6399999856948853},{"id":"https://openalex.org/keywords/feature-extraction-network","display_name":"feature extraction network","score":0.6159999966621399},{"id":"https://openalex.org/keywords/finite-element-method-comparison","display_name":"finite element method comparison","score":0.5740000009536743},{"id":"https://openalex.org/keywords/inverse-problems","display_name":"inverse problems","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.6772000193595886},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C137119250","wikidata":"https://www.wikidata.org/wiki/Q1413101","display_name":"Multigrid method","level":3,"score":0.5541999936103821},{"id":"https://openalex.org/C54067925","wikidata":"https://www.wikidata.org/wiki/Q3607962","display_name":"Elliptic partial differential equation","level":3,"score":0.5205000042915344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5153999924659729},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5085999965667725},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.47040000557899475},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C159674985","wikidata":"https://www.wikidata.org/wiki/Q6823718","display_name":"Method of mean weighted residuals","level":4,"score":0.3224000036716461},{"id":"https://openalex.org/C48753275","wikidata":"https://www.wikidata.org/wiki/Q11216","display_name":"Numerical analysis","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3131999969482422},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C97826883","wikidata":"https://www.wikidata.org/wiki/Q7069659","display_name":"Numerical partial differential equations","level":3,"score":0.30390000343322754},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C127349201","wikidata":"https://www.wikidata.org/wiki/Q753445","display_name":"Numerical integration","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C179603306","wikidata":"https://www.wikidata.org/wiki/Q268493","display_name":"Elliptic curve","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C48395688","wikidata":"https://www.wikidata.org/wiki/Q6823714","display_name":"Method of fundamental solutions","level":5,"score":0.28610000014305115},{"id":"https://openalex.org/C176321772","wikidata":"https://www.wikidata.org/wiki/Q1430640","display_name":"Numerical stability","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C70615421","wikidata":"https://www.wikidata.org/wiki/Q339444","display_name":"Laplace's equation","level":3,"score":0.27129998803138733},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C79518650","wikidata":"https://www.wikidata.org/wiki/Q2081431","display_name":"Integrator","level":3,"score":0.26489999890327454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2533999979496002},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44163-026-02533-0","doi":"https://doi.org/10.1007/s44163-026-02533-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-02533-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02533-0.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","oarl"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:387815fb7f62422c9505a55b8da12e06","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/387815fb7f62422c9505a55b8da12e06","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Discover Artificial Intelligence, Vol 6, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44163-026-02533-0","doi":"https://doi.org/10.1007/s44163-026-02533-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44163-026-02533-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s44163-026-02533-0.pdf","source":{"id":"https://openalex.org/S4210220416","display_name":"Discover Artificial Intelligence","issn_l":"2731-0809","issn":["2731-0809"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","oarl"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Discover Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224997138.pdf","grobid_xml":"https://content.openalex.org/works/W7224997138.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2608816925","https://openalex.org/W2996341379","https://openalex.org/W3011754248","https://openalex.org/W3012922890","https://openalex.org/W3032535486","https://openalex.org/W3101159570","https://openalex.org/W3114286849","https://openalex.org/W3150108261","https://openalex.org/W3190588512","https://openalex.org/W3203473668","https://openalex.org/W4206481447","https://openalex.org/W4220836395","https://openalex.org/W4229447267","https://openalex.org/W4285403904","https://openalex.org/W4293077149","https://openalex.org/W4308334020","https://openalex.org/W4310081603","https://openalex.org/W4366429301","https://openalex.org/W4380998126","https://openalex.org/W4382987553","https://openalex.org/W4388659590","https://openalex.org/W4394923558","https://openalex.org/W4402499338","https://openalex.org/W4404350678","https://openalex.org/W4407048465","https://openalex.org/W4409013854"],"related_works":["https://openalex.org/W4306958315","https://openalex.org/W2987968442","https://openalex.org/W4307288461","https://openalex.org/W3015239968","https://openalex.org/W7213541138","https://openalex.org/W2998882635","https://openalex.org/W2465924250","https://openalex.org/W4409571228","https://openalex.org/W3206130257","https://openalex.org/W3198733440"],"abstract_inverted_index":{"Elliptic":[0],"partial":[1],"differential":[2],"equations":[3,11,35],"(PDEs)":[4],"constitute":[5],"a":[6,240,245,254,283,291],"fundamental":[7],"class":[8],"of":[9,20,33,95,111,155,163,203,280,286],"governing":[10],"in":[12,250],"physics":[13],"and":[14,27,68,116,135,174,187,206,211,225,296],"engineering,":[15],"underpinning":[16],"the":[17,90,108,117,218,226,233,236,258,272],"mathematical":[18],"descriptions":[19],"electrostatic":[21],"potential":[22],"distribution,":[23],"steady-state":[24],"heat":[25],"conduction,":[26],"linear":[28],"elasticity.":[29],"The":[30,84,127,141,157,180,195,263],"numerical":[31,86],"solution":[32,109,120,131],"these":[34],"on":[36,102,138,208,244],"fine":[37,103],"discretization":[38],"grids":[39],"is":[40,82,114,121,144,160],"computationally":[41],"intensive,":[42],"as":[43,61,123],"classical":[44],"iterative":[45],"solvers":[46],"require":[47],"numerous":[48],"sweeps":[49],"to":[50,75,150,191,282],"achieve":[51],"convergence.":[52],"This":[53,288],"computational":[54],"bottleneck":[55],"critically":[56],"hinders":[57],"real-time":[58,91,298],"applications":[59],"such":[60],"online":[62],"process":[63,265],"control,":[64],"interactive":[65],"design":[66],"optimization,":[67],"inverse":[69],"problem":[70],"reconstruction,":[71],"where":[72],"rapid":[73],"response":[74],"changing":[76],"boundary":[77,136,169],"conditions":[78],"or":[79],"source":[80],"terms":[81],"essential.":[83],"traditional":[85],"method":[87,221,228,289],"cannot":[88],"meet":[89],"application":[92],"requirements":[93],"because":[94],"its":[96],"long":[97],"calculation":[98],"time":[99],"when":[100],"solving":[101,295],"grids.":[104],"In":[105,232],"this":[106],"study,":[107],"framework":[110],"deep":[112],"Q-network":[113],"constructed,":[115],"elliptic":[118],"PDE":[119,164],"modeled":[122],"Markov":[124],"decision":[125],"processes.":[126],"state":[128],"space":[129,143],"includes":[130],"field,":[132],"residual":[133,165,189,273],"field":[134],"mark":[137],"discrete":[139,146],"grid.":[140],"action":[142],"11":[145],"corrections":[147],"(\u2212":[148],"0.10":[149,151],"with":[152,271],"an":[153,277],"interval":[154],"0.02).":[156],"reward":[158],"function":[159],"weighted":[161],"sum":[162],"term":[166,171,177],"(weight":[167,172,178],"0.6),":[168],"error":[170],"0.3)":[173],"smooth":[175],"regularization":[176],"0.1).":[179],"feature":[181],"extraction":[182],"network":[183],"uses":[184],"three-layer":[185],"convolution":[186],"two":[188],"blocks":[190],"output":[192],"512-dimensional":[193],"vectors.":[194],"proposed":[196],"DRL":[197,237],"solver":[198,238],"achieves":[199],"relative":[200],"L2":[201],"errors":[202],"0.28%,":[204],"0.39%,":[205],"0.62%":[207],"Poisson,":[209],"Helmholtz,":[210],"anisotropic":[212],"diffusion":[213],"test":[214],"cases,":[215],"respectively,":[216],"outperforming":[217],"finite":[219],"element":[220],"(0.32%,":[222],"0.45%,":[223],"0.78%)":[224],"multigrid":[227,259],"(0.31%,":[229],"0.44%,":[230],"0.76%).":[231],"inference":[234],"phase,":[235],"completes":[239],"single":[241],"forward":[242],"pass":[243],"256":[246],"\u00d7":[247],"2562":[248],"grid":[249],"0.15":[251],"s,":[252],"achieving":[253],"9898-fold":[255],"speedup":[256],"over":[257],"method\u2019s":[260],"14.8":[261],"s.":[262],"training":[264],"converges":[266],"stably":[267],"within":[268],"20,000":[269],"steps,":[270],"norm":[274],"decreasing":[275],"from":[276],"initial":[278],"value":[279,285],"12.4":[281],"final":[284],"0.16.":[287],"provides":[290],"feasible":[292],"way":[293],"for":[294],"controlling":[297],"physical":[299],"fields.":[300]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-11-01T00:00:00"}