Login / Signup
Towards Learning Reward Functions from User Interactions.
Ziming Li
Julia Kiseleva
Maarten de Rijke
Artem Grotov
Published in:
CoRR (2017)
Keyphrases
</>
user interaction
reinforcement learning
learning algorithm
active learning
user feedback
reward function
artificial intelligence
state space
semi supervised
web documents
user behavior
belief propagation
hidden variables
inverse reinforcement learning