Leveraging Good Representations in Linear Contextual Bandits

Authors: Matteo Papini, Andrea Tirinzoni, Marcello Restelli, Alessandro Lazaric, Matteo Pirotta

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

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we empirically validate our theoretical findings in a number of standard contextual bandit problems.
Researcher Affiliation Collaboration 1Politecnico di Milano, Milan, Italy 2Facebook AI Research, Paris, France.
Pseudocode Yes Algorithm 1 LEADER Algorithm
Open Source Code No The paper does not provide an explicit statement or link to open-source code for the described methodology.
Open Datasets Yes Jester Dataset (Goldberg et al., 2001), which consists of joke ratings in a continuous range from 10 to 10 for a total of 100 jokes and 73421 users. [...] Last.fm dataset (Cantador et al., 2011).
Dataset Splits No The paper does not explicitly state specific train/validation/test dataset splits needed for reproduction.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, or memory specifications) used for running its experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup Yes All results are averaged over 20 independent runs, with shaded areas corresponding to 2 standard deviations. We always set the parameters to λ = 1, δ = 0.01, and σ = 0.3. All the representations we consider are normalized to have θ i = 1.