Scaling Imitation Learning in Minecraft

July 06, 2020 · Entered Twilight · 🏛 arXiv.org

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: LICENSE, README.md, agent.py, data_manager.py, dataset.py, get_dataset.py, main.py, minecraft.py, model.py

Authors Artemij Amiranashvili, Nicolai Dorka, Wolfram Burgard, Vladlen Koltun, Thomas Brox arXiv ID 2007.02701 Category cs.LG: Machine Learning Cross-listed cs.AI, stat.ML Citations 17 Venue arXiv.org Repository https://github.com/amiranas/minerl_imitation_learning ⭐ 20 Last Checked 1 month ago

Abstract

Imitation learning is a powerful family of techniques for learning sensorimotor coordination in immersive environments. We apply imitation learning to attain state-of-the-art performance on hard exploration problems in the Minecraft environment. We report experiments that highlight the influence of network architecture, loss function, and data augmentation. An early version of our approach reached second place in the MineRL competition at NeurIPS 2019. Here we report stronger results that can be used as a starting point for future competition entries and related research. Our code is available at https://github.com/amiranas/minerl_imitation_learning.