MineRL Baselines

Towards Solving AI in Open World Environments

This repository contains baselines for various environments in the minerl python package as well as baseline submissions for the MineRL Competition on Sample Efficicent RL @ NeurIPS 2019.

Using the Baselines

The repository is broken up into two main folders:

competition/ # Baseline submissions for NeurIPS comp (MineRLObtainDiamond-v0)
   random_agent/ # git submodule, forks minerllabs/aicrowd_submission_template
   dqn_baseline/ # git submodule, forks ^^
   [...]

general/ # General baselines for the 6+ `minerl` environments!
   chainerrl/ # Baselines written in the Chainer RL framework
   [...]

To get started, do the following:

1. Install the minerl python package: http://www.minerl.io/docs/tutorials/index.html
   • Install JDK 8
   • Install the MineRL Pacakge

     pip3 install --upgrade minerl
     

2. Clone the baselines recursively:

   git clone https://github.com/minerllabs/baselines.git --recurse-submodules 
   

3. Check out the baselines in competition/ and general/!

That's all! :)

Resources

• Documentation for the dataset and the environments is found here!
• Questions about getting started or running these baselines should be directed to the competition forum or discord server
• Technical issues related to the minerl python package should be submitted through the MineRL GitHub page!