The dueling bandit is a learning framework where the feedback information in the learning process is restricted to noisy comparison between a pair of actions. In this paper, we address a dueling bandit problem based on a cost function over a continuous space. We propose a stochastic mirror descent algorithm and show that the algorithm achieves an $O(\sqrt{T\log T})$-regret bound under strong convexity and smoothness assumptions for the cost function. Then, we clarify the equivalence between regret minimization in dueling bandit and convex optimization for the cost function. Moreover, considering a lower bound in convex optimization, it is turned out that our algorithm achieves the optimal convergence rate in convex optimization and the optimal regret in dueling bandit except for a logarithmic factor.

Neural Information Processing Systems http://nips.cc/

This feedback can be system generated or elicited from a human observing the training process. Previous approaches have not been able to scale to complex environments and are constrained to receiving feedback at the state level which can be expensive to collect. To this end, we introduce an approach that scales to more complex domains and extends beyond state-level feedback, thus, reducing the burden on the evaluator.

The acquisition of training data is crucial for machine learning applications.

Gittins index, which can be reinterpreted as an acquisition function.

Machine Learning critically relies on the assumption that the training data is representative of the unseen instances a learner faces at test time.