Online Estimation and Control with Optimal Pathlength Regret.
Gautam GoelBabak HassibiPublished in: L4DC (2022)
Keyphrases
- online learning
- optimal control
- worst case
- online algorithms
- control system
- control problems
- genetic algorithm
- real time
- estimation algorithm
- estimation accuracy
- loss function
- closed form
- control strategy
- density estimation
- markov random field
- control method
- robust estimation
- accurate estimation
- reinforcement learning
- finite horizon
- control policy
- online convex optimization