Login / Signup
Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration.
Weiyan Shi
Yu Li
Saurav Sahay
Zhou Yu
Published in:
EMNLP (Findings) (2021)
Keyphrases
</>
reinforcement learning
machine learning
human interaction
dynamic programming
markov decision processes
function approximation
human behavior
model free
robotic control
multi agent
state space
human experts
human subjects
multi party
action selection
reinforcement learning algorithms