Multimodal Bandits: Regret Lower Bounds and Optimal Algorithms
Authors:
Preprint
Abstract
We consider a stochastic multi-armed bandit problem with i.i.d. rewards where the expected reward function is multimodal with at most m modes. We propose the first known computationally tractable algorithm for computing the solution to the Graves-Lai optimization problem, which in turn enables the implementation of asymptotically optimal algorithms for this bandit problem. The code for the proposed algorithms is publicly available at https://github.com/wilrev/MultimodalBanditsKeywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Statistical learning approaches for global optimization2026
- Optimal Learning for Structured BanditsManagement Science, 2024
- Multimodal Dynamic PricingManagement Science, 2021
- Dynamic Online Pricing with Incomplete Information Using Multiarmed Bandit ExperimentsMarketing Science, 2019
- TheN-armed bandit with unimodal structureMetrika, 1983