State Aggregation Learning from Markov Transition Data

Authors: Yaqi Duan, Tracy Ke, Mengdi Wang

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

Reproducibility Variable Result LLM Response
Research Type Experimental The application of our method to Manhattan traffic data successfully generates a data-driven state aggregation map with nice interpretations. ... We applied our method to a Manhattan taxi-trip dataset, with interesting discoveries. ... Simulation. We test our method on simulations (settings are in the appendix). The results are summarized in Figure 3.
Researcher Affiliation Academia Yaqi Duan Princeton University yaqid@princeton.edu Zheng Tracy Ke Harvard University zke@fas.harvard.edu Mengdi Wang Princeton University mengdiw@princeton.edu
Pseudocode Yes Algorithm 1 Learning the Soft State Aggregation Model.
Open Source Code No The paper does not provide any explicit statement or link to open-source code for the described methodology.
Open Datasets Yes We analyze a dataset of 1.1 × 107 New York city yellow cab trips that were collected in January 2016 [1]. [1] NYC Taxi and Limousine Commission (TLC) trip record data. http://www.nyc.gov/html/tlc/html/about/trip_record_data.shtml. Accessed June 11, 2018.
Dataset Splits No The paper describes using a dataset but does not specify any training, validation, or test splits by percentage or sample count, nor does it refer to predefined splits with citations.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions using a 'vertex hunting algorithm in [21]' and 'feature-based RL [10]' but does not list any specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup No The paper states that 'The algorithm takes as input 27 estimated aggregation distributions as state features' and 'We compute the optimal policy using feature-based RL [10]', but it does not provide specific hyperparameters (e.g., learning rate, batch size, epochs) or detailed training configurations.