Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits

Published in Journal of Machine Learning Research, 2024

This paper develops finite-time analysis for globally nonstationary multi-armed bandit problems. We provide theoretical guarantees for bandits in dynamic environments where the reward distributions change over time, extending the traditional stationary bandit framework to handle time-varying reward structures.

Download paper here

Recommended citation: Komiyama, J., Fouche, E., & Honda, J. (2024). “Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits.” Journal of Machine Learning Research. Vol. 25 (No. 112), 1-56.

Recommended citation: Komiyama, J., Fouche, E., & Honda, J. (2024). "Finite-time Analysis of Globally Nonstationary Multi-Armed Bandits." Journal of Machine Learning Research. Vol. 25 (No. 112), 1-56.
Download Paper