Near-optimal Regret Bounds for Stochastic Shortest Path.

Alon Cohen Haim Kaplan Yishay Mansour Aviv Rosenberg

Published in: CoRR (2020)

Keyphrases

stochastic shortest path
regret bounds
markov decision processes
online learning
lower bound
linear regression
markov decision problems
upper bound
neural network
linear programming
support vector
search space
decision processes
bregman divergences