Apprenticeship Scheduling: Learning to Schedule from Human Experts

Authors: Matthew Gombolay, Reed Jensen, Jessica Stigile, Sung-Hyun Son, Julie Shah

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically demonstrate that this approach accurately learns multifaceted heuristics on both a synthetic data set incorporating jobshop scheduling and vehicle routing problems and a real-world data set consisting of demonstrations of experts solving a weapon-to-target assignment problem.
Researcher Affiliation Collaboration 1Massachusetts Institute of Technology, 77 Massachusetts Avenue, Cambridge, Massachusetts 02139 gombolay@csail.mit.edu, julie a shah@csail.mit.edu 2 MIT Lincoln Laboratory, 244 Wood Street, Lexington, MA 02420 {rjensen,jessica.stigile,sson}@ll.mit.edu
Pseudocode Yes Algorithm 1 Pseudocode for an Apprentice Scheduler
Open Source Code No The paper does not provide a link to open-source code or explicitly state that the code for the described methodology is publicly available.
Open Datasets No The paper describes generating a synthetic data set and collecting a real-world data set, but it does not provide access information (link, citation for public dataset) for either of them.
Dataset Splits Yes We randomly sampled 85% of the data for training and 15% for testing. We trained and tested a decision tree on our pairwise scheduling model via leave-one-out cross-validation using 16 real demonstrations in which a player successfully protected the ship from all enemy missiles.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments (e.g., CPU/GPU models, memory).
Software Dependencies No The paper mentions machine learning techniques used (e.g., decision tree, SVM), but does not specify any software names with version numbers for reproducibility.
Experiment Setup No The paper describes features used for training and data sampling strategy, but it does not specify concrete hyperparameter values or optimizer settings for the machine learning models, which are crucial for reproducing the experimental setup.