Login / Signup
Model-free policy evaluation in Reinforcement Learning via upper solutions.
Denis Belomestny
Ilya Levin
Eric Moulines
Alexey Naumov
Sergey Samsonov
Veronika Zorina
Published in:
CoRR (2021)
Keyphrases
</>
model free
policy evaluation
reinforcement learning
temporal difference
reinforcement learning algorithms
function approximation
policy iteration
least squares
markov decision processes
state space
monte carlo
variance reduction
rl algorithms
multi agent
dynamic programming
reinforcement learning methods