mlsanityData to 7 Oct 2026

Scaling Imitation Learning in Minecraft

arXiv 2007.02701 ↗First posted 6 Jul 2020cs.LG cs.AI stat.MLcited by 12

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

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.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 14 of its 23 references that are in the map. First posted on arXiv 6 Jul 2020.

Builds on

14 of 23 references.

References · 14

  1. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  2. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  3. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  4. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  5. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  6. 2019MineRL: A Large-Scale Dataset of Minecraft Demonstrationscited by 210
  7. 2017Teacher-Student Curriculum Learningcited by 197
  8. 2019Fixup Initialization: Residual Learning Without Normalizationcited by 194
  9. 2016ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learningcited by 178
  10. 2020Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learningcited by 84
  11. 2017Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learningcited by 77
  12. 2020Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learningcited by 18
2 more
  1. 2017Learning Macromanagement in StarCraft from Replays using Deep Learningcited by 5
  2. 2017The Game Imitation: Deep Supervised Convolutional Networks for Quick Video Game AIcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 0; 2023: 6; 2024: 2.

12 papers.

  1. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  2. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  3. 2023Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraftcited by 60
  4. 2023See and Think: Embodied Agent in Virtual Environmentcited by 54
  5. 2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 35
  6. 2021JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learningcited by 28
  7. 2024Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigationcited by 24
  8. 2021SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competitioncited by 20
  9. 2024VIEW: Visual Imitation Learning with Waypointscited by 10
  10. 2023Improving Generalization in Game Agents with Data Augmentation in Imitation Learningcited by 4
  11. 2021Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraftcited by 3
  12. 2021Towards robust and domain agnostic reinforcement learning competitionscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024Zero-shot Imitation Policy via Search in Demonstration Dataset
  2. 2022Behavioral Cloning via Search in Video PreTraining Latent Space
  3. 2020Playing Minecraft with Behavioural Cloning
  4. 2023Behavioral Cloning via Search in Embedded Demonstration Dataset
  5. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
  6. 2023Visual Encoders for Data-Efficient Imitation Learning in Modern Video Games
  7. 2021The MineRL BASALT Competition on Learning from Human Feedback
  8. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances