Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning.

Xuecheng Niu Akinori Ito Takashi Nose

Published in: CoRR (2024)

Keyphrases

learning algorithm
learning systems
mobile learning
active learning
scheduling problem
deep learning
decision trees
reinforcement learning
learning process
supervised learning
online learning
optimal policy
learning tasks
learning community
learning scheme