Real Time In-Game Playstyle Classification Using A Hybrid Probabilistic Supervised Learning Approach
This repository contains the Mario S-TLI and E-TLI datasets from the paper:
"Real Time In-Game Playstyle Classification Using A Hybrid Probabilistic Supervised Learning Approach" by Lindsay John Arendse, Branden Ingram and Benjamin Rosman.
The original source Super Mario Bros evaluation dataset used in this work was created during the user study conducted by Guzdial and Riedl, which consisted of seventy-four human players which played through twelve levels of Super Mario Bros. Please see 'Dataset 1: Mario PCG' at http://guzdial.com/datasets.html.
@INPROCEEDINGS{ArendseIngramRosman2022,
author={Lindsay John Arendse and Branden Ingram and Benjamin Rosman},
title={Real Time In-Game Playstyle Classification Using A Hybrid Probabilistic Supervised Learning Approach},
booktitle={Artificial Intelligence Research.
The Third Southern African Conference for AI Research (SACAIR 2022) Proceedings.
Part of the book series Communications in Computer and Information Science (CCIS)},
year={2022},
publisher={Springer International Publishing}
}
and
@INPROCEEDINGS{GuzdialRiedl2016,
author={Matthew Guzdial and Mark O Riedl},
title={Game level generation from gameplay videos},
booktitle={Proceedings of the Twelfth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment},
year={2016},
url={https://aaai.org/ocs/index.php/AIIDE/AIIDE16/paper/view/14008/13593},
volume={12},
number={1},
pages={44–50}
}