Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804945724> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2804945724 abstract "Dyna-style reinforcement learning is a powerful approach for problems where not much real data is available. The main idea is to supplement real trajectories, or sequences of sampled states over time, with simulated ones sampled from a learned model of the environment. However, in large state spaces, the problem of learning a good generative model of the environment has been open so far. We propose to use deep belief networks to learn an environment model for use in Dyna. We present our approach and validate it empirically on problems where the state observations consist of images. Our results demonstrate that using deep belief networks, which are full generative models, significantly outperforms the use of linear expectation models, proposed in Sutton et al. (2008)" @default.
- W2804945724 created "2018-06-01" @default.
- W2804945724 creator A5065836447 @default.
- W2804945724 creator A5073618265 @default.
- W2804945724 date "2018-05-23" @default.
- W2804945724 modified "2023-09-27" @default.
- W2804945724 title "Dyna Planning using a Feature Based Generative Model." @default.
- W2804945724 cites W104912628 @default.
- W2804945724 cites W1758031947 @default.
- W2804945724 cites W1813659000 @default.
- W2804945724 cites W189596042 @default.
- W2804945724 cites W2100495367 @default.
- W2804945724 cites W2100677568 @default.
- W2804945724 cites W2112796928 @default.
- W2804945724 cites W2134557905 @default.
- W2804945724 cites W2135341757 @default.
- W2804945724 cites W2136163184 @default.
- W2804945724 cites W2136922672 @default.
- W2804945724 cites W2145805610 @default.
- W2804945724 cites W2158164339 @default.
- W2804945724 cites W2161893161 @default.
- W2804945724 cites W3207342693 @default.
- W2804945724 cites W66838807 @default.
- W2804945724 hasPublicationYear "2018" @default.
- W2804945724 type Work @default.
- W2804945724 sameAs 2804945724 @default.
- W2804945724 citedByCount "0" @default.
- W2804945724 crossrefType "posted-content" @default.
- W2804945724 hasAuthorship W2804945724A5065836447 @default.
- W2804945724 hasAuthorship W2804945724A5073618265 @default.
- W2804945724 hasConcept C11413529 @default.
- W2804945724 hasConcept C119857082 @default.
- W2804945724 hasConcept C138885662 @default.
- W2804945724 hasConcept C154945302 @default.
- W2804945724 hasConcept C167966045 @default.
- W2804945724 hasConcept C2776401178 @default.
- W2804945724 hasConcept C39890363 @default.
- W2804945724 hasConcept C41008148 @default.
- W2804945724 hasConcept C41895202 @default.
- W2804945724 hasConcept C48103436 @default.
- W2804945724 hasConcept C97541855 @default.
- W2804945724 hasConceptScore W2804945724C11413529 @default.
- W2804945724 hasConceptScore W2804945724C119857082 @default.
- W2804945724 hasConceptScore W2804945724C138885662 @default.
- W2804945724 hasConceptScore W2804945724C154945302 @default.
- W2804945724 hasConceptScore W2804945724C167966045 @default.
- W2804945724 hasConceptScore W2804945724C2776401178 @default.
- W2804945724 hasConceptScore W2804945724C39890363 @default.
- W2804945724 hasConceptScore W2804945724C41008148 @default.
- W2804945724 hasConceptScore W2804945724C41895202 @default.
- W2804945724 hasConceptScore W2804945724C48103436 @default.
- W2804945724 hasConceptScore W2804945724C97541855 @default.
- W2804945724 hasLocation W28049457241 @default.
- W2804945724 hasOpenAccess W2804945724 @default.
- W2804945724 hasPrimaryLocation W28049457241 @default.
- W2804945724 hasRelatedWork W128438430 @default.
- W2804945724 hasRelatedWork W1728257299 @default.
- W2804945724 hasRelatedWork W1858502558 @default.
- W2804945724 hasRelatedWork W2025741268 @default.
- W2804945724 hasRelatedWork W2133120480 @default.
- W2804945724 hasRelatedWork W2187946878 @default.
- W2804945724 hasRelatedWork W2339749518 @default.
- W2804945724 hasRelatedWork W2618752949 @default.
- W2804945724 hasRelatedWork W2787840125 @default.
- W2804945724 hasRelatedWork W2805543359 @default.
- W2804945724 hasRelatedWork W2874809900 @default.
- W2804945724 hasRelatedWork W2949490796 @default.
- W2804945724 hasRelatedWork W2950774024 @default.
- W2804945724 hasRelatedWork W2963509659 @default.
- W2804945724 hasRelatedWork W2964134604 @default.
- W2804945724 hasRelatedWork W2964232608 @default.
- W2804945724 hasRelatedWork W3013518738 @default.
- W2804945724 hasRelatedWork W3018954346 @default.
- W2804945724 hasRelatedWork W3035413108 @default.
- W2804945724 hasRelatedWork W3193051530 @default.
- W2804945724 isParatext "false" @default.
- W2804945724 isRetracted "false" @default.
- W2804945724 magId "2804945724" @default.
- W2804945724 workType "article" @default.