Scaling Imitation Learning in Minecraft
This work addresses exploration challenges in Minecraft for AI researchers, but it is incremental as it builds on existing imitation learning techniques.
The authors tackled hard exploration problems in Minecraft using imitation learning, achieving state-of-the-art performance and reporting strong results that can serve as a starting point for future research, with an early version placing second in the MineRL competition at NeurIPS 2019.
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.