Goal-Oriented Dialogue Policy Learning from Failures

  • Keting Lu University of Science and Technology of China
  • Shiqi Zhang State University of New York, Binghamton
  • Xiaoping Chen University of Science and Technology of China

Abstract

Reinforcement learning methods have been used for learning dialogue policies. However, learning an effective dialogue policy frequently requires prohibitively many conversations. This is partly because of the sparse rewards in dialogues, and the very few successful dialogues in early learning phase. Hindsight experience replay (HER) enables learning from failures, but the vanilla HER is inapplicable to dialogue learning due to the implicit goals. In this work, we develop two complex HER methods providing different tradeoffs between complexity and performance, and, for the first time, enabled HER-based dialogue policy learning. Experiments using a realistic user simulator show that our HER methods perform better than existing experience replay methods (as applied to deep Q-networks) in learning rate.

Published
2019-07-17
Section
AAAI Technical Track: Humans and AI