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

Yue Wu Jiafan He Quanquan Gu

Published in: CoRR (2023)

Keyphrases

model free
reinforcement learning
multi agent
state space
sample complexity
neural network
vc dimension
function approximation
partially observable domains
rl algorithms
temporal dimension
pac learning
reinforcement learning algorithms
learning theory
noisy data
markov decision processes
sample size
knowledge base