Optimistic PAC Reinforcement Learning: the Instance-Dependent View.

Andrea Tirinzoni Aymen Al Marjani Emilie Kaufmann

Published in: CoRR (2022)

Keyphrases

reinforcement learning
function approximation
state space
reinforcement learning algorithms
learning algorithm
upper bound
multiple views
reinforcement learning methods
robotic control
viewpoint
special case
optimal policy
markov decision processes
sample complexity
model free
noise tolerant