Login / Signup
Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning.
Baolin Peng
Xiujun Li
Jianfeng Gao
Jingjing Liu
Yun-Nung Chen
Kam-Fai Wong
Published in:
ICASSP (2018)
Keyphrases
</>
actor critic
learning algorithm
reinforcement learning
cost function
objective function
neural network
mathematical model
dynamic bayesian networks
reinforcement learning algorithms
approximate dynamic programming