Login / Signup
Improved Worst-Case Regret Bounds for Randomized Least-Squares Value Iteration.
Priyank Agrawal
Jinglin Chen
Nan Jiang
Published in:
AAAI (2021)
Keyphrases
</>
least squares
worst case
linear regression
regret bounds
upper bound
parameter estimation
policy iteration
lower bound
state space
optical flow
markov decision processes
support vector
multi class
nearest neighbor
dynamic programming
infinite horizon
markov decision process