Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model

Authors: Cheng Chen, Canzhe Zhao, Shuai Li6202-6210

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experiments show that our algorithm could simultaneously learn in both stochastic and adversarial environments and is competitive compared to existing methods that are designed for a single environment.
Researcher Affiliation Academia 1 Nanyang Technological University 2 Shanghai Jiao Tong University
Pseudocode Yes Algorithm 1: FTRL-PBM
Open Source Code No The paper does not provide concrete access to source code for the methodology described in this paper.
Open Datasets No The paper describes synthetic data generation parameters and mentions real-world data deferred to Appendix, but does not provide concrete access information (link, DOI, repository, or formal citation) for any publicly available or open dataset used for training.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) needed to reproduce the data partitioning.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup Yes For all experiments, we use n = 10 items and m = 5 positions. For the synthetic data, we set the position examination probabilities to β = (1, 1/5) which are commonly adopted in previous works (Wang et al. 2018; Li, Lattimore, and Szepesv ari 2019). The attractiveness of items are set as α = (0.95, 0.95^2 , ..., 0.95^9 ). We consider two cases of Δ = 0.03 and Δ = 0.01.