Recurrent Existence Determination Through Policy Optimization

Authors: Baoxiang Wang

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experimental analysis demonstrates significant efficiency and accuracy improvement over existing approaches, on both synthetic and real-world datasets. and RED is evaluated empirically on both synthetic datasets, Stained MNIST, and real-world datasets.
Researcher Affiliation Academia Baoxiang Wang The Chinese University of Hong Kong bxwang@cse.cuhk.edu.hk
Pseudocode No The paper describes the algorithm using mathematical formulations and textual descriptions but does not provide structured pseudocode or an algorithm block.
Open Source Code No The paper does not provide any statement or link regarding the availability of its source code.
Open Datasets Yes RED is evaluated empirically on both synthetic datasets, Stained MNIST, and real-world datasets. Stained MNIST is a set of handwritten digits from MNIST. and We test and compare the performance using a dataset publicly available on Kaggle5.
Dataset Splits No The paper mentions a 'training subset' for hyperparameter search but does not provide specific details on dataset splits (training, validation, test percentages or counts) for reproducibility.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper describes the models and algorithms used but does not provide specific software dependencies or version numbers (e.g., libraries, frameworks).
Experiment Setup Yes The hyper-parameters of RED are set to be c = 3, n1 = 18, n2 = 36, n3 = 54 for attention mechanism and γ = 0.95, k = 25, t0 = 10 for prediction aggregation, through a random search on a training subset. and The horizon is fixed to T = 350, where no significant improvement can be observed by further increasing it.