Improved Algorithms for Conservative Exploration in Bandits

Authors: Evrard Garcelon, Mohammad Ghavamzadeh, Alessandro Lazaric, Matteo Pirotta3962-3969

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section we provide empirical evidence of the advantage of the Martingale lower-bound and the action selection process in synthetic and real-data problems.
Researcher Affiliation Industry 1Facebook AI Research, evrard.garcelon@gmail.com, {mgh, lazaric, pirotta}@fb.com
Pseudocode Yes Algorithm 1: CLUCB2 (T = 1) and CLUCB2T
Open Source Code No The paper does not provide any explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes Dataset-based Environments Fig. 5 reports the results using the Jester Dataset (Goldberg et al. 2001)
Dataset Splits No The paper does not explicitly provide specific training/validation/test dataset splits (e.g., percentages or sample counts) needed for reproduction. It mentions using the Jester dataset but not how it was partitioned for training, validation, and testing.
Hardware Specification No The paper does not provide specific details about the hardware used to run its experiments, such as GPU/CPU models, memory, or cloud computing specifications.
Software Dependencies No The paper does not provide specific software dependencies, such as library names with version numbers (e.g., Python, PyTorch, or other relevant packages with their versions).
Experiment Setup Yes The conservative level α is set to 0.05, the horizon n to 106 (T = 1) and δ = 0.01.