Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration.

Priyank Agrawal Jinglin Chen Nan Jiang

Published in: CoRR (2020)

Keyphrases

least squares
worst case
linear regression
regret bounds
lower bound
upper bound
policy iteration
markov decision processes
np hard
dynamic programming
state space
infinite horizon
efficient algorithms for solving
expert advice
statistical models
parameter estimation
mutual information