On Oracle-Efficient PAC RL with Rich Observations.

Christoph Dann Nan Jiang Akshay Krishnamurthy Alekh Agarwal John Langford Robert E. Schapire

Published in: NeurIPS (2018)

Keyphrases

reinforcement learning
sample size
database
real world
learning algorithm
learning process
special case
state space
markov decision processes
pac learning