Two Approaches to Building Collaborative, Task-Oriented Dialog Agents through Self-Play
read the original 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.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
Generative AI evaluation should prioritize real-world utility through stakeholder goals and longitudinal human outcome measurements instead of static benchmark performance.
-
Benchmarked Yet Not Measured -- Generative AI Should be Evaluated Against Real-World Utility
Generative AI evaluation must shift from static benchmark scores to measuring sustained improvements in human capabilities within specific deployment contexts.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.