Login / Signup
A Geometric Perspective on Optimal Representations for Reinforcement Learning.
Marc G. Bellemare
Will Dabney
Robert Dadashi
Adrien Ali Taïga
Pablo Samuel Castro
Nicolas Le Roux
Dale Schuurmans
Tor Lattimore
Clare Lyle
Published in:
NeurIPS (2019)
Keyphrases
</>
reinforcement learning
dynamic programming
function approximation
optimal control
viewpoint
real time
learning algorithm
optimal solution
control policy
object recognition
least squares
geometric information
approximate dynamic programming