{"entities":{"Q7270113":{"pageid":31063085,"ns":120,"title":"Item:Q7270113","lastrevid":104291318,"modified":"2026-06-26T14:06:26Z","type":"item","id":"Q7270113","labels":{"en":{"language":"en","value":"Mesh-RL: Coupled subgrid reinforcement learning"}},"descriptions":{},"aliases":{},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"fd5912e4dab4b881a8eb0eb27e7893fef55176ad","datavalue":{"value":{"entity-type":"item","numeric-id":56887,"id":"Q56887"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7270113$9171DD39-6DEE-4726-B565-A15B5FA7062E","rank":"normal"}],"P1460":[{"mainsnak":{"snaktype":"value","property":"P1460","hash":"57f7fea50d2ce1b39b695c4a1313582eed405e38","datavalue":{"value":{"entity-type":"item","numeric-id":5976449,"id":"Q5976449"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7270113$CB3320C5-3659-4784-A7CA-C9F259CAAFD1","rank":"normal"}],"P21":[{"mainsnak":{"snaktype":"value","property":"P21","hash":"e45353df986fc95b403a059d191fb9115200babb","datavalue":{"value":"2606.26333","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7270113$B1EBF552-0E2A-42EF-B83C-3A04214C040C","rank":"normal"}],"P27":[{"mainsnak":{"snaktype":"value","property":"P27","hash":"160639ea27287d1e568ea4227f99c3c06337a3f8","datavalue":{"value":"10.48550/arXiv.2606.26333","type":"string"},"datatype":"external-id"},"type":"statement","id":"Q7270113$AC09880F-2266-4919-878F-292E689561D6","rank":"normal"}],"P159":[{"mainsnak":{"snaktype":"value","property":"P159","hash":"e948df123e39b2e31346efb1b383ea32c9bc5ea6","datavalue":{"value":{"text":"Mesh-RL: Coupled subgrid reinforcement learning","language":"en"},"type":"monolingualtext"},"datatype":"monolingualtext"},"type":"statement","id":"Q7270113$F8F2DCC2-1E47-4E4C-846B-ECB71B297A72","rank":"normal"}],"P28":[{"mainsnak":{"snaktype":"value","property":"P28","hash":"7e32322c761499fd2686561dfc03964d97ad4752","datavalue":{"value":{"time":"+2026-06-24T00:00:00Z","timezone":0,"before":0,"after":0,"precision":11,"calendarmodel":"http://www.wikidata.org/entity/Q1985727"},"type":"time"},"datatype":"time"},"type":"statement","id":"Q7270113$C93BB3E7-0ACD-4078-92C6-23A22E1B8341","rank":"normal"}],"P22":[{"mainsnak":{"snaktype":"value","property":"P22","hash":"5a9a9eaa7fd7e010f3960691b4ec6b49e1992fea","datavalue":{"value":"cs.LG","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$854D2F29-FEDC-41E7-8035-97EEA659330E","rank":"normal"}],"P43":[{"mainsnak":{"snaktype":"value","property":"P43","hash":"22bc56dc6ee66a87500cdf2b8ff8699cd3b07891","datavalue":{"value":"Behnam Gheshlaghi","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$00E0EEE8-69AA-4DB0-8E09-C093CEF46095","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"58342c03cec0169d06e0fc1cc3eaee3ec251f81c","datavalue":{"value":"Bahador Rashidi","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$74FD3701-BF09-404B-8CF9-66589A7B3F22","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P43","hash":"4315c5f1de7612a746b7abc28ea891da7aa8b982","datavalue":{"value":"Shahin Atakishiyev","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$D7A5F458-B7EA-4647-84A5-78CA8FDDAACC","rank":"normal"}],"P16":[{"mainsnak":{"snaktype":"value","property":"P16","hash":"2faea3cc31a88d523d16f45d79070d863764bb23","datavalue":{"value":{"entity-type":"item","numeric-id":526569,"id":"Q526569"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1642":[{"snaktype":"value","property":"P1642","hash":"a54a2b64f7b8568892d0e11c5b15bda62f19839d","datavalue":{"value":{"entity-type":"item","numeric-id":7270033,"id":"Q7270033"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1642"],"id":"Q7270113$E5943C13-1915-49FB-8131-2CA678C15253","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P16","hash":"0b580f5a4301d66d14b4c33b342c9fb8abae34b0","datavalue":{"value":{"entity-type":"item","numeric-id":2828477,"id":"Q2828477"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","qualifiers":{"P1642":[{"snaktype":"value","property":"P1642","hash":"a54a2b64f7b8568892d0e11c5b15bda62f19839d","datavalue":{"value":{"entity-type":"item","numeric-id":7270033,"id":"Q7270033"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1642"],"id":"Q7270113$63696F4B-7DF5-498E-AF33-525F83AC6767","rank":"normal"}],"P1963":[{"mainsnak":{"snaktype":"value","property":"P1963","hash":"4336b63d33f0a0813fe211cfc546f5e0d65b6db5","datavalue":{"value":"Mesh-RL accelerates temporal-difference learning by partitioning the environment into overlapping subgrids and enforcing boundary-consistent updates, improving convergence speed, cumulative reward, and stability in large or sparse-reward environments while preserving global coherence without modifying the reward function or introducing explicit planning mechanisms.","type":"string"},"datatype":"string"},"type":"statement","qualifiers":{"P1642":[{"snaktype":"value","property":"P1642","hash":"985dbb0e3957a205973fd95bd3fd79ca0980eb5b","datavalue":{"value":{"entity-type":"item","numeric-id":7269921,"id":"Q7269921"},"type":"wikibase-entityid"},"datatype":"wikibase-item"}]},"qualifiers-order":["P1642"],"id":"Q7270113$D236414D-3423-4DAF-96E9-48CE00AF85B5","rank":"normal"}],"P1964":[{"mainsnak":{"snaktype":"value","property":"P1964","hash":"c153d5e8afface037986533ae4839923d75860b9","datavalue":{"value":"Mesh-RL","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$0154FD62-5688-4D81-94ED-FF8095F80624","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1964","hash":"9bec01d55964a3f6828a310a238a2d5839e4027a","datavalue":{"value":"Reinforcement Learning","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$4EEE7C8B-4281-4C2D-B941-AAFAE2075483","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1964","hash":"b7cbab912d58c7545f3cea171d29979d07c9fb03","datavalue":{"value":"Sparse Reward","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$E4FF990B-38E7-4429-80F3-666A18FCA5D9","rank":"normal"},{"mainsnak":{"snaktype":"value","property":"P1964","hash":"d6146fa4935d38167a163f01fb1c198602a02f34","datavalue":{"value":"Domain Decomposition","type":"string"},"datatype":"string"},"type":"statement","id":"Q7270113$00250965-0B70-45C8-AC0F-C6B59FB02D05","rank":"normal"}],"P1642":[{"mainsnak":{"snaktype":"value","property":"P1642","hash":"a54a2b64f7b8568892d0e11c5b15bda62f19839d","datavalue":{"value":{"entity-type":"item","numeric-id":7270033,"id":"Q7270033"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q7270113$6903D44F-B2C4-490B-919F-8FD1D8B96817","rank":"normal"}]},"sitelinks":{"mardi":{"site":"mardi","title":"Mesh-RL: Coupled subgrid reinforcement learning","badges":[],"url":"https://portal.mardi4nfdi.de/wiki/Mesh-RL:_Coupled_subgrid_reinforcement_learning"}}}}}