Decentralized Multi-Agent Linear Bandits with Safety Constraints

Authors: Sanae Amani, Christos Thrampoulidis6627-6635

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

Reproducibility Variable Result LLM Response
Research Type Experimental We present numerical simulations for various network topologies that corroborate our theoretical findings.
Researcher Affiliation Academia Sanae Amani,1 Christos Thrampoulidis 2 1 University of California, Los Angeles 2 University of British Columbia, Vancouver
Pseudocode Yes Algorithm 1: DLUCB for Agent i
Open Source Code No The paper does not contain any explicit statement about making the source code available or a link to a code repository for the described methodology.
Open Datasets No In this section, we evaluate our algorithms performance on synthetic data.
Dataset Splits No The paper states that it evaluates performance on 'synthetic data' and presents parameters for data generation and average over '20 realizations', but does not specify any explicit train, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies, such as library names with version numbers, used to implement or run the experiments.
Experiment Setup Yes All the results shown depict averages over 20 realizations, for which we have chosen d = 5, D = [ 1, 1]5, λ = 1, and σ = 0.1. Moreover, θ is drawn from N(0, I5) and then normalized to unit norm.