thechargedneutron / Statistically-Robust-Bandit-Algorithms

Statistically Robust Bandit Algorithms

This code contains the implementation of the paper "Bandit algorithms: Letting go of logarithmic regret for statistical robustness". The paper is currently under review at AISTATS 2021.

Cite as

@misc{ashutosh2020bandit,
      title={Bandit algorithms: Letting go of logarithmic regret for statistical robustness},
      author={Kumar Ashutosh and Jayakrishnan Nair and Anmol Kagrecha and Krishna Jagannathan},
      year={2020},
      eprint={2006.12038},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

Requirements

• numpy
• matplotlib

Usage

Run python runner.py