First- and Second-Order Bounds for Adversarial Linear Contextual Bandits.
Julia OlkhovskayaJack J. MayoTim van ErvenGergely NeuChen-Yu WeiPublished in: CoRR (2023)
Keyphrases
- high level
- contextual information
- regret bounds
- upper and lower bounds
- upper bound
- lower bound
- higher order
- multi agent
- high order
- closed form
- linear systems
- lower and upper bounds
- context dependent
- context sensitive
- error bounds
- linear functions
- neural network
- multi armed bandits
- piecewise linear
- worst case
- information systems