Matches in SemOpenAlex for { <https://semopenalex.org/work/W2037897789> ?p ?o ?g. }
- W2037897789 endingPage "192" @default.
- W2037897789 startingPage "168" @default.
- W2037897789 abstract "Reinforcement techniques have been successfully used to maximise the expected cumulative reward of statistical dialogue systems. Typically, reinforcement learning is used to estimate the parameters of a dialogue policy which selects the system's responses based on the inferred dialogue state. However, the inference of the dialogue state itself depends on a dialogue model which describes the expected behaviour of a user when interacting with the system. Ideally the parameters of this dialogue model should be also optimised to maximise the expected cumulative reward. This article presents two novel reinforcement algorithms for learning the parameters of a dialogue model. First, the Natural Belief Critic algorithm is designed to optimise the model parameters while the policy is kept fixed. This algorithm is suitable, for example, in systems using a handcrafted policy, perhaps prescribed by other design considerations. Second, the Natural Actor and Belief Critic algorithm jointly optimises both the model and the policy parameters. The algorithms are evaluated on a statistical dialogue system modelled as a Partially Observable Markov Decision Process in a tourist information domain. The evaluation is performed with a user simulator and with real users. The experiments indicate that model parameters estimated to maximise the expected reward function provide improved performance compared to the baseline handcrafted parameters." @default.
- W2037897789 created "2016-06-24" @default.
- W2037897789 creator A5007735982 @default.
- W2037897789 creator A5019913562 @default.
- W2037897789 creator A5072738771 @default.
- W2037897789 date "2012-06-01" @default.
- W2037897789 modified "2023-09-25" @default.
- W2037897789 title "Reinforcement learning for parameter estimation in statistical spoken dialogue systems" @default.
- W2037897789 cites W1970789124 @default.
- W2037897789 cites W1972247907 @default.
- W2037897789 cites W2081445117 @default.
- W2037897789 cites W2103581399 @default.
- W2037897789 cites W2115101920 @default.
- W2037897789 cites W2119015791 @default.
- W2037897789 cites W2119717200 @default.
- W2037897789 cites W2142831953 @default.
- W2037897789 cites W2438667436 @default.
- W2037897789 cites W4255455317 @default.
- W2037897789 doi "https://doi.org/10.1016/j.csl.2011.09.004" @default.
- W2037897789 hasPublicationYear "2012" @default.
- W2037897789 type Work @default.
- W2037897789 sameAs 2037897789 @default.
- W2037897789 citedByCount "44" @default.
- W2037897789 countsByYear W20378977892012 @default.
- W2037897789 countsByYear W20378977892013 @default.
- W2037897789 countsByYear W20378977892014 @default.
- W2037897789 countsByYear W20378977892015 @default.
- W2037897789 countsByYear W20378977892016 @default.
- W2037897789 countsByYear W20378977892017 @default.
- W2037897789 countsByYear W20378977892018 @default.
- W2037897789 countsByYear W20378977892019 @default.
- W2037897789 countsByYear W20378977892020 @default.
- W2037897789 countsByYear W20378977892021 @default.
- W2037897789 countsByYear W20378977892022 @default.
- W2037897789 countsByYear W20378977892023 @default.
- W2037897789 crossrefType "journal-article" @default.
- W2037897789 hasAuthorship W2037897789A5007735982 @default.
- W2037897789 hasAuthorship W2037897789A5019913562 @default.
- W2037897789 hasAuthorship W2037897789A5072738771 @default.
- W2037897789 hasConcept C105795698 @default.
- W2037897789 hasConcept C106189395 @default.
- W2037897789 hasConcept C111368507 @default.
- W2037897789 hasConcept C111919701 @default.
- W2037897789 hasConcept C11413529 @default.
- W2037897789 hasConcept C119857082 @default.
- W2037897789 hasConcept C12725497 @default.
- W2037897789 hasConcept C127313418 @default.
- W2037897789 hasConcept C134261354 @default.
- W2037897789 hasConcept C134306372 @default.
- W2037897789 hasConcept C154945302 @default.
- W2037897789 hasConcept C159886148 @default.
- W2037897789 hasConcept C163836022 @default.
- W2037897789 hasConcept C17098449 @default.
- W2037897789 hasConcept C2776214188 @default.
- W2037897789 hasConcept C33923547 @default.
- W2037897789 hasConcept C36503486 @default.
- W2037897789 hasConcept C41008148 @default.
- W2037897789 hasConcept C48103436 @default.
- W2037897789 hasConcept C97541855 @default.
- W2037897789 hasConcept C98045186 @default.
- W2037897789 hasConcept C98763669 @default.
- W2037897789 hasConceptScore W2037897789C105795698 @default.
- W2037897789 hasConceptScore W2037897789C106189395 @default.
- W2037897789 hasConceptScore W2037897789C111368507 @default.
- W2037897789 hasConceptScore W2037897789C111919701 @default.
- W2037897789 hasConceptScore W2037897789C11413529 @default.
- W2037897789 hasConceptScore W2037897789C119857082 @default.
- W2037897789 hasConceptScore W2037897789C12725497 @default.
- W2037897789 hasConceptScore W2037897789C127313418 @default.
- W2037897789 hasConceptScore W2037897789C134261354 @default.
- W2037897789 hasConceptScore W2037897789C134306372 @default.
- W2037897789 hasConceptScore W2037897789C154945302 @default.
- W2037897789 hasConceptScore W2037897789C159886148 @default.
- W2037897789 hasConceptScore W2037897789C163836022 @default.
- W2037897789 hasConceptScore W2037897789C17098449 @default.
- W2037897789 hasConceptScore W2037897789C2776214188 @default.
- W2037897789 hasConceptScore W2037897789C33923547 @default.
- W2037897789 hasConceptScore W2037897789C36503486 @default.
- W2037897789 hasConceptScore W2037897789C41008148 @default.
- W2037897789 hasConceptScore W2037897789C48103436 @default.
- W2037897789 hasConceptScore W2037897789C97541855 @default.
- W2037897789 hasConceptScore W2037897789C98045186 @default.
- W2037897789 hasConceptScore W2037897789C98763669 @default.
- W2037897789 hasIssue "3" @default.
- W2037897789 hasLocation W20378977891 @default.
- W2037897789 hasOpenAccess W2037897789 @default.
- W2037897789 hasPrimaryLocation W20378977891 @default.
- W2037897789 hasRelatedWork W1515117609 @default.
- W2037897789 hasRelatedWork W1536296381 @default.
- W2037897789 hasRelatedWork W1663497315 @default.
- W2037897789 hasRelatedWork W2146763310 @default.
- W2037897789 hasRelatedWork W2156371714 @default.
- W2037897789 hasRelatedWork W2347690758 @default.
- W2037897789 hasRelatedWork W2963828068 @default.
- W2037897789 hasRelatedWork W3121013427 @default.
- W2037897789 hasRelatedWork W3167472281 @default.
- W2037897789 hasRelatedWork W4381798996 @default.
- W2037897789 hasVolume "26" @default.