Bridging Adversarial and Nonstationary Multi-Armed Bandit
统一了对抗性和非平稳性两种多臂老虎机框架，提出一种新算法，在切换预算下达到最优遗憾界，并匹配下界。
In the multi-armed bandit framework, there are two formulations that are commonly employed to handle time-varying reward distributions: adversarial bandit and nonstationary bandit. Although their oracles, algorithms, and regret analysis differ significantly, we provide a unified formulation in this article that smoothly bridges the two as special cases. The formulation uses an oracle that takes the best action sequences within a switch budget. Depending on the switch budget, it turns into the oracle in hindsight in the adversarial bandit and the dynamic oracle in the nonstationary bandit. We provide algorithms that attain the optimal regret with the matching lower bound. The optimal regret displays distinct behavior in two regimes.