Dueling Bandits with Qualitative Feedback
This work addresses a novel variant of the multi-armed bandit problem for scenarios with qualitative feedback, offering a more efficient approach compared to incremental adaptations of existing methods.
The paper tackles the qualitative dueling bandit problem by proposing direct algorithms that use qualitative feedback to estimate duel outcomes without actual duels, resulting in significant performance improvements over existing dueling bandit algorithms as shown in theoretical and experimental analyses.
We formulate and study a novel multi-armed bandit problem called the qualitative dueling bandit (QDB) problem, where an agent observes not numeric but qualitative feedback by pulling each arm. We employ the same regret as the dueling bandit (DB) problem where the duel is carried out by comparing the qualitative feedback. Although we can naively use classic DB algorithms for solving the QDB problem, this reduction significantly worsens the performance---actually, in the QDB problem, the probability that one arm wins the duel over another arm can be directly estimated without carrying out actual duels. In this paper, we propose such direct algorithms for the QDB problem. Our theoretical analysis shows that the proposed algorithms significantly outperform DB algorithms by incorporating the qualitative feedback, and experimental results also demonstrate vast improvement over the existing DB algorithms.