Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287181768> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4287181768 abstract "Recently regular decision processes have been proposed as a well-behaved form of non-Markov decision process. Regular decision processes are characterised by a transition function and a reward function that depend on the whole history, though regularly (as in regular languages). In practice both the transition and the reward functions can be seen as finite transducers. We study reinforcement learning in regular decision processes. Our main contribution is to show that a near-optimal policy can be PAC-learned in polynomial time in a set of parameters that describe the underlying decision process. We argue that the identified set of parameters is minimal and it reasonably captures the difficulty of a regular decision process." @default.
- W4287181768 created "2022-07-25" @default.
- W4287181768 creator A5013290512 @default.
- W4287181768 creator A5082921554 @default.
- W4287181768 date "2021-05-14" @default.
- W4287181768 modified "2023-09-23" @default.
- W4287181768 title "Efficient PAC Reinforcement Learning in Regular Decision Processes" @default.
- W4287181768 doi "https://doi.org/10.48550/arxiv.2105.06784" @default.
- W4287181768 hasPublicationYear "2021" @default.
- W4287181768 type Work @default.
- W4287181768 citedByCount "0" @default.
- W4287181768 crossrefType "posted-content" @default.
- W4287181768 hasAuthorship W4287181768A5013290512 @default.
- W4287181768 hasAuthorship W4287181768A5082921554 @default.
- W4287181768 hasBestOaLocation W42871817681 @default.
- W4287181768 hasConcept C105795698 @default.
- W4287181768 hasConcept C106189395 @default.
- W4287181768 hasConcept C11413529 @default.
- W4287181768 hasConcept C115988155 @default.
- W4287181768 hasConcept C127413603 @default.
- W4287181768 hasConcept C14036430 @default.
- W4287181768 hasConcept C154945302 @default.
- W4287181768 hasConcept C15744967 @default.
- W4287181768 hasConcept C159886148 @default.
- W4287181768 hasConcept C177264268 @default.
- W4287181768 hasConcept C199360897 @default.
- W4287181768 hasConcept C2984634286 @default.
- W4287181768 hasConcept C33923547 @default.
- W4287181768 hasConcept C41008148 @default.
- W4287181768 hasConcept C539667460 @default.
- W4287181768 hasConcept C67203356 @default.
- W4287181768 hasConcept C77805123 @default.
- W4287181768 hasConcept C78458016 @default.
- W4287181768 hasConcept C86803240 @default.
- W4287181768 hasConcept C97541855 @default.
- W4287181768 hasConcept C98045186 @default.
- W4287181768 hasConceptScore W4287181768C105795698 @default.
- W4287181768 hasConceptScore W4287181768C106189395 @default.
- W4287181768 hasConceptScore W4287181768C11413529 @default.
- W4287181768 hasConceptScore W4287181768C115988155 @default.
- W4287181768 hasConceptScore W4287181768C127413603 @default.
- W4287181768 hasConceptScore W4287181768C14036430 @default.
- W4287181768 hasConceptScore W4287181768C154945302 @default.
- W4287181768 hasConceptScore W4287181768C15744967 @default.
- W4287181768 hasConceptScore W4287181768C159886148 @default.
- W4287181768 hasConceptScore W4287181768C177264268 @default.
- W4287181768 hasConceptScore W4287181768C199360897 @default.
- W4287181768 hasConceptScore W4287181768C2984634286 @default.
- W4287181768 hasConceptScore W4287181768C33923547 @default.
- W4287181768 hasConceptScore W4287181768C41008148 @default.
- W4287181768 hasConceptScore W4287181768C539667460 @default.
- W4287181768 hasConceptScore W4287181768C67203356 @default.
- W4287181768 hasConceptScore W4287181768C77805123 @default.
- W4287181768 hasConceptScore W4287181768C78458016 @default.
- W4287181768 hasConceptScore W4287181768C86803240 @default.
- W4287181768 hasConceptScore W4287181768C97541855 @default.
- W4287181768 hasConceptScore W4287181768C98045186 @default.
- W4287181768 hasLocation W42871817681 @default.
- W4287181768 hasLocation W42871817682 @default.
- W4287181768 hasOpenAccess W4287181768 @default.
- W4287181768 hasPrimaryLocation W42871817681 @default.
- W4287181768 hasRelatedWork W1574991376 @default.
- W4287181768 hasRelatedWork W2023122515 @default.
- W4287181768 hasRelatedWork W2163284801 @default.
- W4287181768 hasRelatedWork W2895923634 @default.
- W4287181768 hasRelatedWork W3020239300 @default.
- W4287181768 hasRelatedWork W3096874164 @default.
- W4287181768 hasRelatedWork W3121013427 @default.
- W4287181768 hasRelatedWork W3188631122 @default.
- W4287181768 hasRelatedWork W4205805428 @default.
- W4287181768 hasRelatedWork W4308702637 @default.
- W4287181768 isParatext "false" @default.
- W4287181768 isRetracted "false" @default.
- W4287181768 workType "article" @default.