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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Building a dialogue agent to fulfill complex tasks, such as travel planning,is challenging because the agent has to learn to collectively complete multiplesubtasks. For example, the agent needs to reserve a hotel and book a flight sothat there leaves enough time for commute between arrival and hotel check-in.This paper addresses this challenge by formulating the task in the mathematicalframework of options over Markov Decision Processes (MDPs), and proposing ahierarchical deep reinforcement learning approach to learning a dialoguemanager that operates at different temporal scales. The dialogue managerconsists of: (1) a top-level dialogue policy that selects among subtasks oroptions, (2) a low-level dialogue policy that selects primitive actions tocomplete the subtask given by the top-level policy, and (3) a global statetracker that helps ensure all cross-subtask constraints be satisfied.Experiments on a travel planning task with simulated and real users show thatour approach leads to significant improvements over three baselines, two basedon handcrafted rules and the other based on flat deep reinforcement learning.

Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning