English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improvingthe effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposedframework that extends the Dyna-Q algorithm to integrate planning fortask-completion dialogue policy learning. To obviate DDQ's high dependency onthe quality of simulated experiences, we incorporate an RNN-based discriminatorin D3Q to differentiate simulated experience from real user experience in orderto control the quality of training data. Experiments show that D3Qsignificantly outperforms DDQ by controlling the quality of simulatedexperience used for planning. The effectiveness and robustness of D3Q isfurther demonstrated in a domain extension setting, where the agent'scapability of adapting to a changing environment is tested.

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning