Scaling Imitation Learning in Minecraft

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.

References in corpus (7)

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Human-level performance in first-person multiplayer games with population-based deep reinforcement learning
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Deep Q-learning from Demonstrations
• Fixup Initialization: Residual Learning Without Normalization
• The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AI

Cited by in corpus (3)

• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
• Towards robust and domain agnostic reinforcement learning competitions
• SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition