Login / Signup
Successor Uncertainties: exploration and uncertainty in temporal difference learning.
David Janz
Jiri Hron
José Miguel Hernández-Lobato
Katja Hofmann
Sebastian Tschiatschek
Published in:
CoRR (2018)
Keyphrases
</>
temporal difference learning
fixed point
game playing
function approximation
evaluation function
reinforcement learning
approximate value iteration
temporal difference
reinforcement learning algorithms
markov decision process
artificial neural networks
monte carlo
neural network
function approximators