Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits

Authors: Ronshee Chawla, Daniel Vial, Sanjay Shakkottai, R. Srikant

ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate Algorithm 1 in the context unaware setting and Algorithm 3 in the partially context aware setting, and verify their insights through synthetic simulations.
Researcher Affiliation Academia 1Chandra Family Department of Electrical and Computer Engineering, University of Texas, Austin, TX, USA 2Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign, IL, USA.
Pseudocode Yes Algorithm 1 (at agent i)Algorithm 2 Arm RecommendationAlgorithm 3 (at agent i)Algorithm 4 Dividing M most recent unique arm recommendations
Open Source Code No The paper does not contain any explicit statements about releasing source code or provide links to a code repository.
Open Datasets No The paper uses synthetic simulations where 'Arm means are generated uniformly at random from [0, 1) in Figure 1 and [2, 4) in Figure 2', but does not provide access information (link, DOI, repository, or formal citation) for a public dataset.
Dataset Splits No The paper conducts synthetic simulations and does not describe any training, validation, or test dataset splits (e.g., percentages or counts) or refer to standard predefined splits.
Hardware Specification No The paper describes simulation parameters ('K arm means... generated uniformly at random', 'set β = 3', 'UCB parameter α is set to 15') but does not specify any hardware components (e.g., GPU/CPU models, memory, or cloud instances) used for running the experiments.
Software Dependencies No The paper does not list specific software components with version numbers (e.g., programming languages, libraries, or frameworks with their versions) that would be needed to replicate the experiment.
Experiment Setup Yes We assume an equal number (N/M) of agents learning each bandit, set β = 3 and the size of the sticky set S = K/N in these simulations. The UCB parameter α is set to 15 in Figure 1 and 30 in Figure 2.