Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890189120> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2890189120 endingPage "1432" @default.
- W2890189120 startingPage "1422" @default.
- W2890189120 abstract "We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and value function classes exclusively through standard optimization primitives -- and therefore represent computationally efficient alternatives to prior algorithms that require enumeration. With stochastic hidden state dynamics, we prove that the only known sample-efficient algorithm, OLIVE, cannot be implemented in the oracle model. We also present several examples that illustrate fundamental challenges of tractable PAC reinforcement learning in such general settings." @default.
- W2890189120 created "2018-09-27" @default.
- W2890189120 creator A5005003250 @default.
- W2890189120 creator A5008181744 @default.
- W2890189120 creator A5015082848 @default.
- W2890189120 creator A5015966835 @default.
- W2890189120 creator A5036435487 @default.
- W2890189120 creator A5084108666 @default.
- W2890189120 date "2018-01-01" @default.
- W2890189120 modified "2023-09-24" @default.
- W2890189120 title "On oracle-efficient PAC RL with rich observations" @default.
- W2890189120 hasPublicationYear "2018" @default.
- W2890189120 type Work @default.
- W2890189120 sameAs 2890189120 @default.
- W2890189120 citedByCount "19" @default.
- W2890189120 countsByYear W28901891202019 @default.
- W2890189120 countsByYear W28901891202020 @default.
- W2890189120 countsByYear W28901891202021 @default.
- W2890189120 crossrefType "proceedings-article" @default.
- W2890189120 hasAuthorship W2890189120A5005003250 @default.
- W2890189120 hasAuthorship W2890189120A5008181744 @default.
- W2890189120 hasAuthorship W2890189120A5015082848 @default.
- W2890189120 hasAuthorship W2890189120A5015966835 @default.
- W2890189120 hasAuthorship W2890189120A5036435487 @default.
- W2890189120 hasAuthorship W2890189120A5084108666 @default.
- W2890189120 hasConcept C11413529 @default.
- W2890189120 hasConcept C126255220 @default.
- W2890189120 hasConcept C14036430 @default.
- W2890189120 hasConcept C14646407 @default.
- W2890189120 hasConcept C154945302 @default.
- W2890189120 hasConcept C185592680 @default.
- W2890189120 hasConcept C198531522 @default.
- W2890189120 hasConcept C199360897 @default.
- W2890189120 hasConcept C33923547 @default.
- W2890189120 hasConcept C41008148 @default.
- W2890189120 hasConcept C43617362 @default.
- W2890189120 hasConcept C45374587 @default.
- W2890189120 hasConcept C48103436 @default.
- W2890189120 hasConcept C55166926 @default.
- W2890189120 hasConcept C78458016 @default.
- W2890189120 hasConcept C80444323 @default.
- W2890189120 hasConcept C86803240 @default.
- W2890189120 hasConcept C97541855 @default.
- W2890189120 hasConceptScore W2890189120C11413529 @default.
- W2890189120 hasConceptScore W2890189120C126255220 @default.
- W2890189120 hasConceptScore W2890189120C14036430 @default.
- W2890189120 hasConceptScore W2890189120C14646407 @default.
- W2890189120 hasConceptScore W2890189120C154945302 @default.
- W2890189120 hasConceptScore W2890189120C185592680 @default.
- W2890189120 hasConceptScore W2890189120C198531522 @default.
- W2890189120 hasConceptScore W2890189120C199360897 @default.
- W2890189120 hasConceptScore W2890189120C33923547 @default.
- W2890189120 hasConceptScore W2890189120C41008148 @default.
- W2890189120 hasConceptScore W2890189120C43617362 @default.
- W2890189120 hasConceptScore W2890189120C45374587 @default.
- W2890189120 hasConceptScore W2890189120C48103436 @default.
- W2890189120 hasConceptScore W2890189120C55166926 @default.
- W2890189120 hasConceptScore W2890189120C78458016 @default.
- W2890189120 hasConceptScore W2890189120C80444323 @default.
- W2890189120 hasConceptScore W2890189120C86803240 @default.
- W2890189120 hasConceptScore W2890189120C97541855 @default.
- W2890189120 hasLocation W28901891201 @default.
- W2890189120 hasOpenAccess W2890189120 @default.
- W2890189120 hasPrimaryLocation W28901891201 @default.
- W2890189120 hasRelatedWork W107583932 @default.
- W2890189120 hasRelatedWork W1850488217 @default.
- W2890189120 hasRelatedWork W2119738618 @default.
- W2890189120 hasRelatedWork W2121863487 @default.
- W2890189120 hasRelatedWork W2145339207 @default.
- W2890189120 hasRelatedWork W2545659366 @default.
- W2890189120 hasRelatedWork W2912399346 @default.
- W2890189120 hasRelatedWork W2962723383 @default.
- W2890189120 hasRelatedWork W2963049774 @default.
- W2890189120 hasRelatedWork W2963971282 @default.
- W2890189120 hasRelatedWork W2964054583 @default.
- W2890189120 hasRelatedWork W2964299116 @default.
- W2890189120 hasRelatedWork W2965004202 @default.
- W2890189120 hasRelatedWork W2990210896 @default.
- W2890189120 hasRelatedWork W2991929641 @default.
- W2890189120 hasRelatedWork W2995638039 @default.
- W2890189120 hasRelatedWork W3006052551 @default.
- W2890189120 hasRelatedWork W3026228308 @default.
- W2890189120 hasRelatedWork W3035273634 @default.
- W2890189120 hasRelatedWork W3046395471 @default.
- W2890189120 hasVolume "31" @default.
- W2890189120 isParatext "false" @default.
- W2890189120 isRetracted "false" @default.
- W2890189120 magId "2890189120" @default.
- W2890189120 workType "article" @default.