Matches in SemOpenAlex for { <https://semopenalex.org/work/W3165825116> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3165825116 abstract "The reinforcement learning problem of finding a control policy that minimizes the minimum time objective for the Mountain Car environment is considered. Particularly, a class of parameterized nonlinear feedback policies is optimized over to reach the top of the highest mountain peak in minimum time. The optimization is carried out using quasi-Stochastic Gradient Descent (qSGD) methods. In attempting to find the optimal minimum time policy, a new parameterized policy approach is considered that seeks to learn an optimal policy parameter for different regions of the state space, rather than rely on a single macroscopic policy parameter for the entire state space. This partitioned parameterized policy approach is shown to outperform the uniform parameterized policy approach and lead to greater generalization than prior methods, where the Mountain Car became trapped in circular trajectories in the state space." @default.
- W3165825116 created "2021-06-07" @default.
- W3165825116 creator A5068512521 @default.
- W3165825116 date "2021-05-28" @default.
- W3165825116 modified "2023-09-27" @default.
- W3165825116 title "Improving Generalization in Mountain Car Through the Partitioned Parameterized Policy Approach via Quasi-Stochastic Gradient Descent." @default.
- W3165825116 cites W1600437712 @default.
- W3165825116 cites W2071983464 @default.
- W3165825116 cites W2089411859 @default.
- W3165825116 cites W2113913482 @default.
- W3165825116 cites W2121863487 @default.
- W3165825116 cites W2132414174 @default.
- W3165825116 cites W3153049565 @default.
- W3165825116 cites W3175771377 @default.
- W3165825116 cites W3210638057 @default.
- W3165825116 hasPublicationYear "2021" @default.
- W3165825116 type Work @default.
- W3165825116 sameAs 3165825116 @default.
- W3165825116 citedByCount "1" @default.
- W3165825116 countsByYear W31658251162021 @default.
- W3165825116 crossrefType "posted-content" @default.
- W3165825116 hasAuthorship W3165825116A5068512521 @default.
- W3165825116 hasConcept C105795698 @default.
- W3165825116 hasConcept C111919701 @default.
- W3165825116 hasConcept C11413529 @default.
- W3165825116 hasConcept C121332964 @default.
- W3165825116 hasConcept C126255220 @default.
- W3165825116 hasConcept C134306372 @default.
- W3165825116 hasConcept C153258448 @default.
- W3165825116 hasConcept C154945302 @default.
- W3165825116 hasConcept C158622935 @default.
- W3165825116 hasConcept C165464430 @default.
- W3165825116 hasConcept C177148314 @default.
- W3165825116 hasConcept C2775924081 @default.
- W3165825116 hasConcept C2778572836 @default.
- W3165825116 hasConcept C33923547 @default.
- W3165825116 hasConcept C41008148 @default.
- W3165825116 hasConcept C47446073 @default.
- W3165825116 hasConcept C48103436 @default.
- W3165825116 hasConcept C50644808 @default.
- W3165825116 hasConcept C62520636 @default.
- W3165825116 hasConcept C72434380 @default.
- W3165825116 hasConcept C97541855 @default.
- W3165825116 hasConceptScore W3165825116C105795698 @default.
- W3165825116 hasConceptScore W3165825116C111919701 @default.
- W3165825116 hasConceptScore W3165825116C11413529 @default.
- W3165825116 hasConceptScore W3165825116C121332964 @default.
- W3165825116 hasConceptScore W3165825116C126255220 @default.
- W3165825116 hasConceptScore W3165825116C134306372 @default.
- W3165825116 hasConceptScore W3165825116C153258448 @default.
- W3165825116 hasConceptScore W3165825116C154945302 @default.
- W3165825116 hasConceptScore W3165825116C158622935 @default.
- W3165825116 hasConceptScore W3165825116C165464430 @default.
- W3165825116 hasConceptScore W3165825116C177148314 @default.
- W3165825116 hasConceptScore W3165825116C2775924081 @default.
- W3165825116 hasConceptScore W3165825116C2778572836 @default.
- W3165825116 hasConceptScore W3165825116C33923547 @default.
- W3165825116 hasConceptScore W3165825116C41008148 @default.
- W3165825116 hasConceptScore W3165825116C47446073 @default.
- W3165825116 hasConceptScore W3165825116C48103436 @default.
- W3165825116 hasConceptScore W3165825116C50644808 @default.
- W3165825116 hasConceptScore W3165825116C62520636 @default.
- W3165825116 hasConceptScore W3165825116C72434380 @default.
- W3165825116 hasConceptScore W3165825116C97541855 @default.
- W3165825116 hasLocation W31658251161 @default.
- W3165825116 hasOpenAccess W3165825116 @default.
- W3165825116 hasPrimaryLocation W31658251161 @default.
- W3165825116 hasRelatedWork W123062064 @default.
- W3165825116 hasRelatedWork W2130906191 @default.
- W3165825116 hasRelatedWork W2332431765 @default.
- W3165825116 hasRelatedWork W2381033265 @default.
- W3165825116 hasRelatedWork W2739160792 @default.
- W3165825116 hasRelatedWork W2783940602 @default.
- W3165825116 hasRelatedWork W2936912184 @default.
- W3165825116 hasRelatedWork W2949205035 @default.
- W3165825116 hasRelatedWork W2952132225 @default.
- W3165825116 hasRelatedWork W2952469083 @default.
- W3165825116 hasRelatedWork W2953409117 @default.
- W3165825116 hasRelatedWork W2953881522 @default.
- W3165825116 hasRelatedWork W2955291764 @default.
- W3165825116 hasRelatedWork W2959336552 @default.
- W3165825116 hasRelatedWork W2990558591 @default.
- W3165825116 hasRelatedWork W3010790156 @default.
- W3165825116 hasRelatedWork W3011677145 @default.
- W3165825116 hasRelatedWork W3012021832 @default.
- W3165825116 hasRelatedWork W3148518187 @default.
- W3165825116 hasRelatedWork W3158775690 @default.
- W3165825116 isParatext "false" @default.
- W3165825116 isRetracted "false" @default.
- W3165825116 magId "3165825116" @default.
- W3165825116 workType "article" @default.