Linear contextual bandits represent a fundamental class of models with numerous real-world applications, and it is critical to developing algorithms that can effectively manage noise with unknown variance, ensuring provable guarantees for both worst-case constant-variance noise and deterministic reward scenarios.

This bound naturally breaks into two components.

The agent pulls an arm and observes the corresponding return provided by the environment.

However, it may not be available in practice.

UCB, wherein agents cooperatively minimize the group regret under the coordination of a central server.

Lijun Zhang is the corresponding author.