Paraphrase Generation with Deep Reinforcement Learning.

Zichao Li Xin Jiang Lifeng Shang Hang Li

Published in: CoRR (2017)

Keyphrases

reinforcement learning
question answering
robotic control
markov decision processes
reinforcement learning algorithms
function approximation
generation process
belief nets
optimal policy
state space
machine learning
learning process
model free
temporal difference
case study
deep learning
social networks