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

Gautam Goel Naman Agarwal Karan Singh Elad Hazan

Published in: L4DC (2023)

Keyphrases

online algorithms
competitive ratio
online learning
lower bound
asymptotically optimal
learning algorithm
worst case
reward function
average case
sufficient conditions
optimal policy
single machine
initially unknown
decision boundary
upper bound
probability distribution
e learning