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

When learning task-oriented dialogue (ToD) agents, reinforcement learning(RL) techniques can naturally be utilized to train dialogue strategies toachieve user-specific goals. Prior works mainly focus on adopting advanced RLtechniques to train the ToD agents, while the design of the reward function isnot well studied. This paper aims at answering the question of how toefficiently learn and leverage a reward function for training end-to-end (E2E)ToD agents. Specifically, we introduce two generalized objectives forreward-function learning, inspired by the classical learning-to-rankliterature. Further, we utilize the learned reward function to guide thetraining of the E2E ToD agent. With the proposed techniques, we achievecompetitive results on the E2E response-generation task on the Multiwoz 2.0dataset. Source code and checkpoints are publicly released athttps://github.com/Shentao-YANG/Fantastic_Reward_ICLR2023.

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems