Matches in SemOpenAlex for { <https://semopenalex.org/work/W2807588596> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2807588596 abstract "Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decision problems. Other methods, such as bootstrap sampling, have no mechanism for uncertainty that does not come from the observed data. We highlight why this can be a crucial shortcoming and propose a simple remedy through addition of a randomized untrainable `prior' network to each ensemble member. We prove that this approach is efficient with linear representations, provide simple illustrations of its efficacy with nonlinear representations and show that this approach scales to large-scale problems far better than previous attempts." @default.
- W2807588596 created "2018-06-13" @default.
- W2807588596 creator A5015899120 @default.
- W2807588596 creator A5029807267 @default.
- W2807588596 creator A5030260581 @default.
- W2807588596 date "2018-06-08" @default.
- W2807588596 modified "2023-09-27" @default.
- W2807588596 title "Randomized Prior Functions for Deep Reinforcement Learning" @default.
- W2807588596 cites W1975950946 @default.
- W2807588596 cites W2121863487 @default.
- W2807588596 cites W2124181495 @default.
- W2807588596 cites W2470693974 @default.
- W2807588596 cites W2507592741 @default.
- W2807588596 cites W2786928559 @default.
- W2807588596 hasPublicationYear "2018" @default.
- W2807588596 type Work @default.
- W2807588596 sameAs 2807588596 @default.
- W2807588596 citedByCount "19" @default.
- W2807588596 countsByYear W28075885962018 @default.
- W2807588596 countsByYear W28075885962019 @default.
- W2807588596 countsByYear W28075885962020 @default.
- W2807588596 countsByYear W28075885962021 @default.
- W2807588596 crossrefType "posted-content" @default.
- W2807588596 hasAuthorship W2807588596A5015899120 @default.
- W2807588596 hasAuthorship W2807588596A5029807267 @default.
- W2807588596 hasAuthorship W2807588596A5030260581 @default.
- W2807588596 hasConcept C106131492 @default.
- W2807588596 hasConcept C111472728 @default.
- W2807588596 hasConcept C119857082 @default.
- W2807588596 hasConcept C121332964 @default.
- W2807588596 hasConcept C138885662 @default.
- W2807588596 hasConcept C140779682 @default.
- W2807588596 hasConcept C154945302 @default.
- W2807588596 hasConcept C2778755073 @default.
- W2807588596 hasConcept C2780586882 @default.
- W2807588596 hasConcept C31972630 @default.
- W2807588596 hasConcept C41008148 @default.
- W2807588596 hasConcept C62520636 @default.
- W2807588596 hasConcept C97541855 @default.
- W2807588596 hasConceptScore W2807588596C106131492 @default.
- W2807588596 hasConceptScore W2807588596C111472728 @default.
- W2807588596 hasConceptScore W2807588596C119857082 @default.
- W2807588596 hasConceptScore W2807588596C121332964 @default.
- W2807588596 hasConceptScore W2807588596C138885662 @default.
- W2807588596 hasConceptScore W2807588596C140779682 @default.
- W2807588596 hasConceptScore W2807588596C154945302 @default.
- W2807588596 hasConceptScore W2807588596C2778755073 @default.
- W2807588596 hasConceptScore W2807588596C2780586882 @default.
- W2807588596 hasConceptScore W2807588596C31972630 @default.
- W2807588596 hasConceptScore W2807588596C41008148 @default.
- W2807588596 hasConceptScore W2807588596C62520636 @default.
- W2807588596 hasConceptScore W2807588596C97541855 @default.
- W2807588596 hasLocation W28075885961 @default.
- W2807588596 hasOpenAccess W2807588596 @default.
- W2807588596 hasPrimaryLocation W28075885961 @default.
- W2807588596 hasRelatedWork W1522301498 @default.
- W2807588596 hasRelatedWork W1850488217 @default.
- W2807588596 hasRelatedWork W2039522160 @default.
- W2807588596 hasRelatedWork W2121863487 @default.
- W2807588596 hasRelatedWork W2145339207 @default.
- W2807588596 hasRelatedWork W2155027007 @default.
- W2807588596 hasRelatedWork W2280163991 @default.
- W2807588596 hasRelatedWork W2489939061 @default.
- W2807588596 hasRelatedWork W2736601468 @default.
- W2807588596 hasRelatedWork W2755611049 @default.
- W2807588596 hasRelatedWork W2770939375 @default.
- W2807588596 hasRelatedWork W2781726626 @default.
- W2807588596 hasRelatedWork W2890211540 @default.
- W2807588596 hasRelatedWork W2949608212 @default.
- W2807588596 hasRelatedWork W2951266961 @default.
- W2807588596 hasRelatedWork W2962723954 @default.
- W2807588596 hasRelatedWork W2963238274 @default.
- W2807588596 hasRelatedWork W2964059111 @default.
- W2807588596 hasRelatedWork W2964067469 @default.
- W2807588596 hasRelatedWork W3205279445 @default.
- W2807588596 isParatext "false" @default.
- W2807588596 isRetracted "false" @default.
- W2807588596 magId "2807588596" @default.
- W2807588596 workType "article" @default.