MineRL 2019 competition challenged participants to train sample-efficient agents to play Minecraft, by using a dataset of human gameplay and a limit number of steps the environment. We approached this task with behavioural cloning by predicting what actions human players would take, and reached fifth place in the final ranking. Despite being a simple algorithm, we observed the performance of such an approach can vary significantly, based on when the training is stopped. In this paper, we detail our submission to the competition, run further experiments to study how performance varied over training and study how different engineering decisions affected these results.
@article{arxiv.2005.03374,
title = {Playing Minecraft with Behavioural Cloning},
author = {Anssi Kanervisto and Janne Karttunen and Ville Hautamäki},
journal= {arXiv preprint arXiv:2005.03374},
year = {2020}
}
Comments
To appear in Post Proceedings of the Competitions & Demonstrations Track @ NeurIPS2019. Source code available at https://github.com/Miffyli/minecraft-bc