Linear Programming for Large-Scale Markov Decision Problems

Authors: Alan Malek, Yasin Abbasi-Yadkori, Peter Bartlett

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Preliminary experiments show the effectiveness of the proposed algorithm in a queuing application.
Researcher Affiliation Academia Yasin Abbasi-Yadkori YASIN.ABBASIYADKORI@QUT.EDU.AU Queensland University of Technology, Brisbane, QLD, Australia 4000 Peter L. Bartlett BARTLETT@EECS.BERKELEY.EDU University of California, Berkeley, CA 94720 and Queensland University of Technology, Brisbane, QLD, Australia 4000 Alan Malek MALEK@EECS.BERKELEY.EDU University of California, Berkeley, CA 94720
Pseudocode Yes The algorithm is shown in Figure 1.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets No The paper applies its algorithm to a 'four-dimensional discrete-time queueing network' and specifies parameters for this network, but it does not mention a publicly available dataset, nor does it provide a link, DOI, or formal citation for data access. It describes a simulated environment rather than using an external public dataset.
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts) for training, validation, or testing for the simulated queueing network.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. It only mentions 'simulations'.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers.
Experiment Setup Yes We used a1 = a3 = .08, d1 = d2 = .12, and d3 = d4 = .28, and buffer sizes B1 = B4 = 38, B2 = B3 = 25 as the parameters of the network. ... our learning rate began at 10 4 and halved every 2000 iterations.