Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play [article]

Arkady Arkhangorodsky, Scot Fang, Victoria Knight, Ajay Nagesh, Maria Ryskina, Kevin Knight
2021 arXiv   pre-print
Task-oriented dialog systems are often trained on human/human dialogs, such as collected from Wizard-of-Oz interfaces. However, human/human corpora are frequently too small for supervised training to be effective. This paper investigates two approaches to training agent-bots and user-bots through self-play, in which they autonomously explore an API environment, discovering communication strategies that enable them to solve the task. We give empirical results for both reinforcement learning and game-theoretic equilibrium finding.
arXiv:2109.09597v1 fatcat:vjyxsflsb5givhv6luefjpyoj4