End-to-End Learning and Intervention in Games

Authors: Jiayang Li, Jing Yu, Yu Nie, Zhaoran Wang

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The analytical results are validated using several real-world problems. [...] We give real-world examples to demonstrate the potential applications of the proposed framework. [...] 4 Numerical experiments
Researcher Affiliation Academia Jiayang Li Northwestern University jiayangli2024@u.northwestern.edu Jing Yu Northwestern University jingyu2021@u.northwestern.edu Yu (Marco) Nie Northwestern University y-nie@northwestern.edu Zhaoran Wang Northwestern University zhaoranwang@gmail.com
Pseudocode No The paper describes algorithms and refers to appendices for implementation details (e.g., 'See Appendix B.2 for a globally convergent algorithm and implementation details.'), but no pseudocode or algorithm blocks are present in the provided text.
Open Source Code No The paper refers to a third-party Python library 'cvxpylayers' and provides its GitHub link ('https://github.com/cvxgrp/cvxpylayers'). However, it does not provide source code specifically developed for the methodology presented in this paper.
Open Datasets No The paper states: 'We randomly generated N source-sink demand matrices, representing the travel demand in N different periods. We use the true cost functions to generate observations by finding equilibrium traffic flows, and round them to the nearest 0.1.' This indicates the use of synthetically generated data rather than a publicly available or open dataset.
Dataset Splits No The paper mentions 'The model is trained using the stochastic gradient decent method. Figure 7 shows the training process under 4 different hyperparameters settings.' However, it does not provide specific details on how the data was split into training, validation, and test sets, such as percentages or sample counts.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as GPU models, CPU specifications, or cloud computing instances.
Software Dependencies No The paper mentions 'the Python library cvxpylayers' and provides a GitHub link, but it does not specify a version number for this or any other software component, which is required for reproducibility.
Experiment Setup Yes The paper states: 'Figure 7 shows the training process under 4 different hyperparameters settings.' This indicates that specific hyperparameter settings were part of the experimental setup, even if the values themselves are not explicitly listed in the provided text.