Adapting to Delays and Data in Adversarial Multi-Armed Bandits

Authors: Andras Gyorgy, Pooria Joulani

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We analyze variants of the Exp3 algorithm that tune their step size using only information (about the losses and delays) available at the time of the decisions, and obtain regret guarantees that adapt to the observed (rather than the worst-case) sequences of delays and/or losses. First, through a remarkably simple proof technique, we show that with proper tuning of the step size, the algorithm achieves an optimal (up to logarithmic factors) regret of order p log(K)(TK + D) both in expectation and in high probability
Researcher Affiliation Industry 1Deep Mind, London, UK. Correspondence to: Andr as Gy orgy <agyorgy@deepmind.com>, Pooria Joulani <pjoulani@deepmind.com>.
Pseudocode Yes Algorithm 1: Delay-Adaptive Exp3 (DAda-Exp3).
Open Source Code No The paper does not mention providing open-source code for the described methodology.
Open Datasets No This paper is theoretical and does not involve experimental training on a dataset.
Dataset Splits No This paper is theoretical and does not involve dataset splits for training/validation/test.
Hardware Specification No The paper is theoretical and does not describe hardware specifications for running experiments.
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe experimental setup details like hyperparameters or training settings.