Provably Efficient Reinforcement Learning via Surprise Bound.

Hanlin Zhu Ruosong Wang Jason D. Lee

Published in: AISTATS (2023)

Keyphrases

reinforcement learning
worst case
computationally expensive
real time
machine learning
lower bound
upper bound
lightweight
cost effective
genetic algorithm
artificial intelligence
case study
multiscale
multi agent
least squares
function approximation