Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory.

Yunhao Li Yunyi Yang Xiaojun Quan Jianxing Yu

Published in: CoRR (2021)

Keyphrases

learning process
action selection
learning algorithm
bayesian networks
reinforcement learning
learning systems
knowledge acquisition
natural language
supervised learning
learning tasks
cognitive load
long term memory
inverse reinforcement learning
agent learns