Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension.

Yue Wu Jiafan He Quanquan Gu

Published in: UAI (2023)

Keyphrases

model free
reinforcement learning
upper bound
optimal policy
pac learning
reinforcement learning algorithms
function approximation
learning theory
sample size
multi agent
learning algorithm
state space
special case
vc dimension
training data
temporal difference
data sets