DAL: A Practical Prior-Free Black-Box Framework for Non-Stationary Bandits
This provides a practical solution for adaptive decision-making in dynamic environments, though it is incremental as it builds on existing stationary bandit algorithms.
The paper tackles the problem of non-stationary bandits without prior knowledge by introducing the Detection Augmented Learning (DAL) framework, which consistently surpasses current state-of-the-art methods across diverse scenarios, including synthetic benchmarks and real-world datasets.
We introduce a practical, black-box framework termed Detection Augmented Learning (DAL) for the problem of non-stationary bandits without prior knowledge of the underlying non-stationarity. DAL accepts any stationary bandit algorithm as input and augments it with a change detector, enabling applicability to all common bandit variants. Extensive experimentation demonstrates that DAL consistently surpasses current state-of-the-art methods across diverse non-stationary scenarios, including synthetic benchmarks and real-world datasets, underscoring its versatility and scalability. We provide theoretical insights into DAL's strong empirical performance, complemented by thorough experimental validation.