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

2021/09/20 by Arkhangorodsky, Arkady, Fang, Scot, Knight, Victoria +3
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2109.09597

Abstract

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.

Related

• Toward Self-learning End-to-End Task-Oriented Dialog Systems
• Building Task Bots with Self-learning for Enhanced Adaptability, Extensibility, and Factuality
• A User Simulator for Task-Completion Dialogues
• Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition
• Collaborative Multi-Agent Dialogue Model Training Via Reinforcement\n Learning