Domain-Specific Multi-Agent Dialog Policy Learning in Multi-Domain Task-Oriented Scenarios.

Li Tang Yuke Si Longbiao Wang Jianwu Dang

Published in: Interspeech (2021)

Keyphrases

domain specific
multi domain
multi agent
learning process
learning algorithm
reinforcement learning
active learning
optimal policy
supervised learning
general purpose
learning tasks
learning scenarios
pairwise
prior knowledge
tutorial dialogue