Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space.

Anas Barakat Ilyas Fatkhullin Niao He

Published in: ICML (2023)

Keyphrases

reinforcement learning
variance reduction
state action space
function approximation
monte carlo
learning algorithm
machine learning
decision trees
support vector
lower bound
active learning
state space
sample size