Online estimation and control with optimal pathlength regret.
Gautam GoelBabak HassibiPublished in: CoRR (2021)
Keyphrases
- online learning
- optimal control
- worst case
- dynamic programming
- online algorithms
- estimation accuracy
- optimal design
- control system
- real time
- data acquisition
- accurate estimation
- estimation error
- control strategy
- loss function
- parameter estimation
- lower bound
- learning algorithm
- game theory
- linear regression
- active learning
- optimal strategy
- search engine
- neural network
- asymptotically optimal
- control policy
- data sets