A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning

TL;DR

This survey reviews recent advances and challenges in applying reinforcement learning to dialogue policy learning in task-oriented dialogue systems, highlighting key problems, solutions, and future directions.

Contribution

It provides a comprehensive categorization and analysis of recent RL-based methods for dialogue policy learning, identifying major challenges and potential research avenues.

Findings

Identification of key problems in RL-based dialogue policy learning

Summary of recent solutions and methods in the field

Guidance for future research in dialogue management

Abstract

Dialogue Policy Learning is a key component in a task-oriented dialogue system (TDS) that decides the next action of the system given the dialogue state at each turn. Reinforcement Learning (RL) is commonly chosen to learn the dialogue policy, regarding the user as the environment and the system as the agent. Many benchmark datasets and algorithms have been created to facilitate the development and evaluation of dialogue policy based on RL. In this paper, we survey recent advances and challenges in dialogue policy from the prescriptive of RL. More specifically, we identify the major problems and summarize corresponding solutions for RL-based dialogue policy learning. Besides, we provide a comprehensive survey of applying RL to dialogue policy learning by categorizing recent methods into basic elements in RL. We believe this survey can shed a light on future research in dialogue management.