Matches in SemOpenAlex for { <https://semopenalex.org/work/W1279312> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W1279312 endingPage "1386" @default.
- W1279312 startingPage "1385" @default.
- W1279312 abstract "An important subclass of reinforcement learning problems are those that exhibit only discrete uncertainty: the agent's environment is known to be sampled from a finite set of possible worlds. In contrast to generic reinforcement learning problems, it is possible to efficiently compute the Bayes-optimal policy for many discrete uncertainty RL domains. We demonstrate empirically that the Bayes-optimal policy can result in substantially and significantly improved performance relative to a state of the art probably approximately correct RL algorithm. Our second contribution is to bound the error of using slightly noisy estimates of the discrete set of possible Markov decision process parameters during learning. We suggest that this is an important and probable situation, given such models will often be constructed from finite sets of noisy, real-world data. We demonstrate good empirical performance on a simulated machine repair problem when using noisy parameter estimates." @default.
- W1279312 created "2016-06-24" @default.
- W1279312 creator A5084989076 @default.
- W1279312 date "2012-06-04" @default.
- W1279312 modified "2023-09-26" @default.
- W1279312 title "Bayes-optimal reinforcement learning for discrete uncertainty domains" @default.
- W1279312 cites W1497039698 @default.
- W1279312 cites W1505937442 @default.
- W1279312 cites W2111833414 @default.
- W1279312 cites W2116459397 @default.
- W1279312 cites W2124352385 @default.
- W1279312 cites W2125710232 @default.
- W1279312 cites W2489939061 @default.
- W1279312 cites W2963214119 @default.
- W1279312 doi "https://doi.org/10.5555/2343896.2344019" @default.
- W1279312 hasPublicationYear "2012" @default.
- W1279312 type Work @default.
- W1279312 sameAs 1279312 @default.
- W1279312 citedByCount "11" @default.
- W1279312 countsByYear W12793122013 @default.
- W1279312 countsByYear W12793122014 @default.
- W1279312 countsByYear W12793122016 @default.
- W1279312 countsByYear W12793122019 @default.
- W1279312 countsByYear W12793122020 @default.
- W1279312 crossrefType "proceedings-article" @default.
- W1279312 hasAuthorship W1279312A5084989076 @default.
- W1279312 hasConcept C105795698 @default.
- W1279312 hasConcept C106189395 @default.
- W1279312 hasConcept C107673813 @default.
- W1279312 hasConcept C111919701 @default.
- W1279312 hasConcept C112972136 @default.
- W1279312 hasConcept C11413529 @default.
- W1279312 hasConcept C119857082 @default.
- W1279312 hasConcept C126255220 @default.
- W1279312 hasConcept C134306372 @default.
- W1279312 hasConcept C154945302 @default.
- W1279312 hasConcept C159886148 @default.
- W1279312 hasConcept C162392398 @default.
- W1279312 hasConcept C176248197 @default.
- W1279312 hasConcept C177264268 @default.
- W1279312 hasConcept C199360897 @default.
- W1279312 hasConcept C207201462 @default.
- W1279312 hasConcept C32254414 @default.
- W1279312 hasConcept C33923547 @default.
- W1279312 hasConcept C41008148 @default.
- W1279312 hasConcept C97541855 @default.
- W1279312 hasConcept C98045186 @default.
- W1279312 hasConceptScore W1279312C105795698 @default.
- W1279312 hasConceptScore W1279312C106189395 @default.
- W1279312 hasConceptScore W1279312C107673813 @default.
- W1279312 hasConceptScore W1279312C111919701 @default.
- W1279312 hasConceptScore W1279312C112972136 @default.
- W1279312 hasConceptScore W1279312C11413529 @default.
- W1279312 hasConceptScore W1279312C119857082 @default.
- W1279312 hasConceptScore W1279312C126255220 @default.
- W1279312 hasConceptScore W1279312C134306372 @default.
- W1279312 hasConceptScore W1279312C154945302 @default.
- W1279312 hasConceptScore W1279312C159886148 @default.
- W1279312 hasConceptScore W1279312C162392398 @default.
- W1279312 hasConceptScore W1279312C176248197 @default.
- W1279312 hasConceptScore W1279312C177264268 @default.
- W1279312 hasConceptScore W1279312C199360897 @default.
- W1279312 hasConceptScore W1279312C207201462 @default.
- W1279312 hasConceptScore W1279312C32254414 @default.
- W1279312 hasConceptScore W1279312C33923547 @default.
- W1279312 hasConceptScore W1279312C41008148 @default.
- W1279312 hasConceptScore W1279312C97541855 @default.
- W1279312 hasConceptScore W1279312C98045186 @default.
- W1279312 hasLocation W12793121 @default.
- W1279312 hasOpenAccess W1279312 @default.
- W1279312 hasPrimaryLocation W12793121 @default.
- W1279312 hasRelatedWork W1024197927 @default.
- W1279312 hasRelatedWork W1582436621 @default.
- W1279312 hasRelatedWork W1850488217 @default.
- W1279312 hasRelatedWork W1988526405 @default.
- W1279312 hasRelatedWork W2044097402 @default.
- W1279312 hasRelatedWork W2116459397 @default.
- W1279312 hasRelatedWork W2119567691 @default.
- W1279312 hasRelatedWork W2121863487 @default.
- W1279312 hasRelatedWork W2124352385 @default.
- W1279312 hasRelatedWork W2144794447 @default.
- W1279312 hasRelatedWork W2154623234 @default.
- W1279312 hasRelatedWork W2489939061 @default.
- W1279312 hasRelatedWork W2787825303 @default.
- W1279312 hasRelatedWork W2894616334 @default.
- W1279312 hasRelatedWork W2902806543 @default.
- W1279312 hasRelatedWork W2948345763 @default.
- W1279312 hasRelatedWork W2950680678 @default.
- W1279312 hasRelatedWork W2963214119 @default.
- W1279312 hasRelatedWork W3210962293 @default.
- W1279312 hasRelatedWork W602901760 @default.
- W1279312 isParatext "false" @default.
- W1279312 isRetracted "false" @default.
- W1279312 magId "1279312" @default.
- W1279312 workType "article" @default.