Matches in SemOpenAlex for { <https://semopenalex.org/work/W4309200314> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4309200314 abstract "Deep Q-learning based algorithms have been applied successfully in many decision making problems, while their theoretical foundations are not as well understood. In this paper, we study a Fitted Q-Iteration with two-layer ReLU neural network parameterization, and find the sample complexity guarantees for the algorithm. Our approach estimates the Q-function in each iteration using a convex optimization problem. We show that this approach achieves a sample complexity of $tilde{mathcal{O}}(1/epsilon^{2})$, which is order-optimal. This result holds for a countable state-spaces and does not require any assumptions such as a linear or low rank structure on the MDP." @default.
- W4309200314 created "2022-11-24" @default.
- W4309200314 creator A5005811512 @default.
- W4309200314 creator A5064822688 @default.
- W4309200314 creator A5077692482 @default.
- W4309200314 date "2022-11-14" @default.
- W4309200314 modified "2023-09-26" @default.
- W4309200314 title "On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization" @default.
- W4309200314 doi "https://doi.org/10.48550/arxiv.2211.07675" @default.
- W4309200314 hasPublicationYear "2022" @default.
- W4309200314 type Work @default.
- W4309200314 citedByCount "0" @default.
- W4309200314 crossrefType "posted-content" @default.
- W4309200314 hasAuthorship W4309200314A5005811512 @default.
- W4309200314 hasAuthorship W4309200314A5064822688 @default.
- W4309200314 hasAuthorship W4309200314A5077692482 @default.
- W4309200314 hasBestOaLocation W43092003141 @default.
- W4309200314 hasConcept C110729354 @default.
- W4309200314 hasConcept C112680207 @default.
- W4309200314 hasConcept C11413529 @default.
- W4309200314 hasConcept C114614502 @default.
- W4309200314 hasConcept C118615104 @default.
- W4309200314 hasConcept C121332964 @default.
- W4309200314 hasConcept C126255220 @default.
- W4309200314 hasConcept C14036430 @default.
- W4309200314 hasConcept C145446738 @default.
- W4309200314 hasConcept C154945302 @default.
- W4309200314 hasConcept C162324750 @default.
- W4309200314 hasConcept C164226766 @default.
- W4309200314 hasConcept C178790620 @default.
- W4309200314 hasConcept C185592680 @default.
- W4309200314 hasConcept C198531522 @default.
- W4309200314 hasConcept C202887219 @default.
- W4309200314 hasConcept C2524010 @default.
- W4309200314 hasConcept C2777303404 @default.
- W4309200314 hasConcept C2778445095 @default.
- W4309200314 hasConcept C2779227376 @default.
- W4309200314 hasConcept C28826006 @default.
- W4309200314 hasConcept C33923547 @default.
- W4309200314 hasConcept C41008148 @default.
- W4309200314 hasConcept C50522688 @default.
- W4309200314 hasConcept C50644808 @default.
- W4309200314 hasConcept C62520636 @default.
- W4309200314 hasConcept C74902906 @default.
- W4309200314 hasConcept C78458016 @default.
- W4309200314 hasConcept C86803240 @default.
- W4309200314 hasConcept C97355855 @default.
- W4309200314 hasConceptScore W4309200314C110729354 @default.
- W4309200314 hasConceptScore W4309200314C112680207 @default.
- W4309200314 hasConceptScore W4309200314C11413529 @default.
- W4309200314 hasConceptScore W4309200314C114614502 @default.
- W4309200314 hasConceptScore W4309200314C118615104 @default.
- W4309200314 hasConceptScore W4309200314C121332964 @default.
- W4309200314 hasConceptScore W4309200314C126255220 @default.
- W4309200314 hasConceptScore W4309200314C14036430 @default.
- W4309200314 hasConceptScore W4309200314C145446738 @default.
- W4309200314 hasConceptScore W4309200314C154945302 @default.
- W4309200314 hasConceptScore W4309200314C162324750 @default.
- W4309200314 hasConceptScore W4309200314C164226766 @default.
- W4309200314 hasConceptScore W4309200314C178790620 @default.
- W4309200314 hasConceptScore W4309200314C185592680 @default.
- W4309200314 hasConceptScore W4309200314C198531522 @default.
- W4309200314 hasConceptScore W4309200314C202887219 @default.
- W4309200314 hasConceptScore W4309200314C2524010 @default.
- W4309200314 hasConceptScore W4309200314C2777303404 @default.
- W4309200314 hasConceptScore W4309200314C2778445095 @default.
- W4309200314 hasConceptScore W4309200314C2779227376 @default.
- W4309200314 hasConceptScore W4309200314C28826006 @default.
- W4309200314 hasConceptScore W4309200314C33923547 @default.
- W4309200314 hasConceptScore W4309200314C41008148 @default.
- W4309200314 hasConceptScore W4309200314C50522688 @default.
- W4309200314 hasConceptScore W4309200314C50644808 @default.
- W4309200314 hasConceptScore W4309200314C62520636 @default.
- W4309200314 hasConceptScore W4309200314C74902906 @default.
- W4309200314 hasConceptScore W4309200314C78458016 @default.
- W4309200314 hasConceptScore W4309200314C86803240 @default.
- W4309200314 hasConceptScore W4309200314C97355855 @default.
- W4309200314 hasLocation W43092003141 @default.
- W4309200314 hasOpenAccess W4309200314 @default.
- W4309200314 hasPrimaryLocation W43092003141 @default.
- W4309200314 hasRelatedWork W1533959244 @default.
- W4309200314 hasRelatedWork W1916943071 @default.
- W4309200314 hasRelatedWork W2146698032 @default.
- W4309200314 hasRelatedWork W2356755074 @default.
- W4309200314 hasRelatedWork W2364765674 @default.
- W4309200314 hasRelatedWork W2380955682 @default.
- W4309200314 hasRelatedWork W2916889016 @default.
- W4309200314 hasRelatedWork W3097823105 @default.
- W4309200314 hasRelatedWork W4309200314 @default.
- W4309200314 hasRelatedWork W970142403 @default.
- W4309200314 isParatext "false" @default.
- W4309200314 isRetracted "false" @default.
- W4309200314 workType "article" @default.