Minimal Exploration in Structured Stochastic Bandits
This work addresses the challenge of efficient exploration in bandit problems for researchers and practitioners, offering a novel algorithmic approach that is not incremental but provides a new paradigm for handling structured environments.
The paper tackles the problem of minimizing regret in structured stochastic bandits by introducing a framework that covers various known structures and developing the OSSB algorithm, which matches an asymptotic instance-specific regret lower bound and outperforms existing algorithms like Thompson sampling in numerical experiments.
This paper introduces and addresses a wide class of stochastic bandit problems where the function mapping the arm to the corresponding reward exhibits some known structural properties. Most existing structures (e.g. linear, Lipschitz, unimodal, combinatorial, dueling, ...) are covered by our framework. We derive an asymptotic instance-specific regret lower bound for these problems, and develop OSSB, an algorithm whose regret matches this fundamental limit. OSSB is not based on the classical principle of "optimism in the face of uncertainty" or on Thompson sampling, and rather aims at matching the minimal exploration rates of sub-optimal arms as characterized in the derivation of the regret lower bound. We illustrate the efficiency of OSSB using numerical experiments in the case of the linear bandit problem and show that OSSB outperforms existing algorithms, including Thompson sampling.