Best of Both Worlds in Online Control: Competitive Ratio and Policy Regret.

Gautam Goel Naman Agarwal Karan Singh Elad Hazan

Published in: CoRR (2022)

Keyphrases

online algorithms
competitive ratio
online learning
lower bound
worst case
asymptotically optimal
learning algorithm
reward function
single machine
average case
optimal strategy
upper bound
computational complexity
simulated annealing