Logarithmic Regret for Adversarial Online Control.
Dylan J. FosterMax SimchowitzPublished in: CoRR (2020)
Keyphrases
- online learning
- online algorithms
- worst case
- control system
- multi agent
- real time
- neural network
- expert advice
- control strategy
- game theory
- active learning
- learning algorithm
- lower bound
- data acquisition
- website
- closed loop
- information systems
- convex optimization
- control problems
- information retrieval
- online convex optimization