Login / Signup

Replicating Complex Dialogue Policy of Humans via Offline Imitation Learning with Supervised Regularization.

Zhoujian SunChenyang ZhaoZhengxing HuangNai Ding
Published in: CoRR (2023)
Keyphrases
  • imitation learning
  • real time
  • feature selection
  • human teacher
  • learning algorithm
  • reinforcement learning
  • pairwise
  • active learning
  • supervised learning
  • multi modal
  • maximum margin