Task-Completion Dialogue Policy Learning

3 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

MiuLab/DDQ ACL 2018

During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience.

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

MiuLab/D3Q EMNLP 2018

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning for task-completion dialogue policy learning.

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

CrickWu/Swtich-DDQ 19 Nov 2018

Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences.