{"entities":{"Q6482957":{"pageid":13979111,"ns":120,"title":"Item:Q6482957","lastrevid":37832173,"modified":"2024-09-09T13:13:03Z","type":"item","id":"Q6482957","labels":{"en":{"language":"en","value":"CORL (Causal discovery with Ordering-based Reinforcement Learning)"}},"descriptions":{"en":{"language":"en","value":"A reinforcement learning approach to DAG learning by treatening a vertex order problem as a multi-step Markov decision process, implement the ordering generating process with an encoder-decoder architecture, and finally use RL to optimize the proposed model based on the reward mechanisms designed for each ordering"}},"aliases":{"en":[{"language":"en","value":"CORL"}]},"claims":{"P31":[{"mainsnak":{"snaktype":"value","property":"P31","hash":"3549c24f9ade438a3be5e15249f51b5c11a6425f","datavalue":{"value":{"entity-type":"item","numeric-id":127020,"id":"Q127020"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6482957$fcb4a85a-4f47-0f62-d2c2-4aa85409d98d","rank":"normal"}],"P286":[{"mainsnak":{"snaktype":"value","property":"P286","hash":"e17e2cc1cc9e8f62442cfa61c5b40aafcd895e76","datavalue":{"value":{"entity-type":"item","numeric-id":6486440,"id":"Q6486440"},"type":"wikibase-entityid"},"datatype":"wikibase-item"},"type":"statement","id":"Q6482957$97f51258-4b7f-698c-d4d2-d96987c47d8d","rank":"normal"}]},"sitelinks":{}}}}