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

Xuecheng Niu Akinori Ito Takashi Nose

Published in: IEEE Access (2024)

Keyphrases

learning algorithm
learning process
deep learning
active learning
learning systems
learning analytics
learning tasks
action selection
inductive inference
learning scheme
learning scenarios
evaluation function
learning problems
unsupervised learning
supervised learning
training data
e learning