Contextual Continuum Bandits: Static Versus Dynamic Regret.
Arya AkhavanKarim LouniciMassimiliano PontilAlexandre B. TsybakovPublished in: CoRR (2024)
Keyphrases
- dynamic environments
- contextual information
- online learning
- learning algorithm
- dynamic analysis
- dynamically changing
- context sensitive
- mobile robot
- worst case
- dynamic programming
- lower bound
- feature selection
- game theory
- social networks
- artificial intelligence
- neural network
- regret bounds
- dynamic constraints
- multi armed bandits