Benchmarking Uncertainty Estimates with Deep Reinforcement Learning for Dialogue Policy Optimisation

Citation Author(s):: Christopher Tegho

Christopher Tegho, Pawel Budzianowski, Milica Gasic
Submitted by:: Christopher Tegho
Last updated:: 19 April 2018 - 12:50pm
Document Type:: Presentation
Document Year:: 2018
Event:: ICASSP 2018
Presenters:: Christopher Tegho
Paper Code:: 2190

Categories:: Audio and Acoustic Signal Processing
Keywords:: HLT-L2.2: Language and Dialog Modeling

Log in to post comments

ICASSP Presentation (1).pdf

ICASSP Presentation (1).pdf (474)

Thumbs Up

CITE

QUESTIONS?