MineRL: Towards AI in Minecraft

Welcome to documentation for the MineRL project and its related repositories and components!

What is MineRL

MineRL is a research project started at Carnegie Mellon University aimed at developing various aspects of artificial intelligence within Minecraft. In short MineRL consists of several major components:

• MineRL-v0 Dataset – One of the largest imitation learning datasets with over 60 million frames of recorded human player data. The dataset includes a set of environments which highlight many of the hardest problems in modern-day Reinforcement Learning: sparse rewards and hierarchical policies.

• minerl – A rich python3 package for doing artificial intelligence research in Minecraft. This includes two major submodules. We develop minerl in our spare time, please consider supporting us on Patreon

  • minerl.env – A growing set of OpenAI Gym environments in Minecraft. These environments leverage a synchronous, stable, and fast fork of Microsoft Malmo called MineRLEnv.

  • minerl.data – The main python module for ext with the MineRL-v0 dataset

Tutorials and Guides

• Installation
• Hello World: Your First Agent
  • Creating an environment
  • Taking actions
  • No-op actions and a better policy
• Downloading and Sampling The Dataset
  • Introduction
  • Setting up environment variables
  • Downloading the MineRL Dataset with minerl.data.download
  • Sampling the Dataset with buffered_batch_iter
  • Moderate Human Demonstrations
• K-means exploration
• Visualizing The Data minerl.viewer
• Interactive Mode minerl.interactor
• Creating A Custom Environment
  • Introduction
  • Setup
  • Contruct the Environment Class
  • Modify the World
  • Set the Initial Agent Inventory
  • Create Reward Functionality
  • Construct a Quit Handler
  • Allow the Agent to Place Water
  • Give Extra Observations
  • Set the Time
  • Other Functions to Implement
  • Using the Environment
• Using Minecraft Commands
  • Introduction
  • How Can MC Commands speed up training?
  • Adding the ChatAction to your envspec
  • Abstracted Command Sending
  • Advanced use

MineRL Environments

• General Information
• Environment Handlers
  • Environment Handlers
  • Spaces
  • Observations
  • Actions
• MineRL Diamond Competition Intro Track Environments
  • MineRLTreechop-v0
  • MineRLNavigate-v0
  • MineRLNavigateDense-v0
  • MineRLNavigateExtreme-v0
  • MineRLNavigateExtremeDense-v0
  • MineRLObtainDiamond-v0
  • MineRLObtainDiamondDense-v0
  • MineRLObtainIronPickaxe-v0
  • MineRLObtainIronPickaxeDense-v0
• MineRL Diamond Competition Research Track Environments
  • MineRLTreechopVectorObf-v0
  • MineRLNavigateVectorObf-v0
  • MineRLNavigateDenseVectorObf-v0
  • MineRLNavigateExtremeVectorObf-v0
  • MineRLNavigateExtremeDenseVectorObf-v0
  • MineRLObtainDiamondVectorObf-v0
  • MineRLObtainDiamondDenseVectorObf-v0
  • MineRLObtainIronPickaxeVectorObf-v0
  • MineRLObtainIronPickaxeDenseVectorObf-v0
• MineRL BASALT Competition Environments
  • MineRLBasaltFindCave-v0
  • MineRLBasaltMakeWaterfall-v0
  • MineRLBasaltCreateVillageAnimalPen-v0
  • MineRLBasaltBuildVillageHouse-v0

Notes

• Performance tips
  • Slowdown in obfuscated environments
  • Faster alternative to xvfb
• Links to papers and projects
  • Presentations
  • MineRL papers
  • 2019 competitor code/papers
  • 2020 competitor code/papers
  • Other papers that use the MineRL environment
  • Other
• Windows FAQ
  • The The system cannot find the path specified error (installing)
  • The freeze_support error (multiprocessing)

MineRL package API Reference

• minerl.env
  • MineRLEnv
  • InstanceManager
• minerl.data
  • MineRLv0
• minerl.herobraine
  • Handlers
  • Agent Handlers
  • Server Handlers

Indices and tables

• Index

• Module Index

• Search Page