Login / Signup
Manipulating the Distributions of Experience used for Self-Play Learning in Expert Iteration.
Dennis J. N. J. Soemers
Éric Piette
Matthew Stephenson
Cameron Browne
Published in:
CoG (2020)
Keyphrases
</>
learning algorithm
learning process
prior knowledge
background knowledge
objective function
online learning
unsupervised learning
learning systems
learning problems
active learning
supervised learning
human experts
learning scheme
inductive inference