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

Recent works usually address Dialog policy learning DPL by training areinforcement learning (RL) agent to determine the best dialog action. However,existing works on deep RL require a large volume of agent-user interactions toachieve acceptable performance. In this paper, we propose to make full use ofthe plain text knowledge from the pre-trained language model to accelerate theRL agent's learning speed. Specifically, we design a dialog action-awaretransformer encoder (DaTrans), which integrates a new fine-tuning procedurenamed masked last action task to encourage DaTrans to be dialog-aware anddistils action-specific features. Then, DaTrans is further optimized in an RLsetting with ongoing interactions and evolves through exploration in the dialogaction space toward maximizing long-term accumulated rewards. The effectivenessand efficiency of the proposed model are demonstrated with both simulatorevaluation and human evaluation.

Dialog Action-Aware Transformer for Dialog Policy Learning