GBOSE: Generalized Bandit Orthogonalized Semiparametric Estimation
This work addresses the limitation of parametric assumptions in bandit algorithms for applications like mobile health recommendations, though it is incremental as it builds upon existing action filtering methods.
The paper tackles the problem of sequential decision-making in multi-armed bandits by proposing a new algorithm with a semi-parametric reward model, achieving state-of-the-art regret complexity among semi-parametric algorithms and demonstrating superiority in simulations for cases with over two arms.
In sequential decision-making scenarios i.e., mobile health recommendation systems revenue management contextual multi-armed bandit algorithms have garnered attention for their performance. But most of the existing algorithms are built on the assumption of a strictly parametric reward model mostly linear in nature. In this work we propose a new algorithm with a semi-parametric reward model with state-of-the-art complexity of upper bound on regret amongst existing semi-parametric algorithms. Our work expands the scope of another representative algorithm of state-of-the-art complexity with a similar reward model by proposing an algorithm built upon the same action filtering procedures but provides explicit action selection distribution for scenarios involving more than two arms at a particular time step while requiring fewer computations. We derive the said complexity of the upper bound on regret and present simulation results that affirm our methods superiority out of all prevalent semi-parametric bandit algorithms for cases involving over two arms.