Cascaded LSTMs based Deep Reinforcement Learning for Goal-driven Dialogue.

Yue Ma Xiaojie Wang Zhenjiang Dong Hong Chen

Published in: CoRR (2019)

Keyphrases

goal driven
reinforcement learning
function approximation
service composition
dialogue system
software product line
model free
state space
face detection
semantic web services
human machine
natural language
mixed initiative
artificial intelligence
multi agent
optimal policy
markov decision processes