The Diamond challenge is now a part of the [BASALT] competition!
Standard reinforcement learning methods require months to years of game time to attain human performance in complex games such as Go and StarCraft. In our competition (held at NeurIPS in 2019, 2020, and 2021), participants developed a system to obtain a diamond in Minecraft using only four days of training time. This year, the Diamond challenge will be folded into the BASALT competition as a more well-defined task than the primary BASALT tasks.
The MineRL Diamond challenge offers a set of Gym environments paired with human demonstrations. The goal of providing the demonstrations is to enable participants to tackle the problem in a sample-efficient manner. In previous years, we vectorized obfuscated the action and observation spaces to promote the development of generalizable solutions. This year, participants can use any creative solution and are not required to use the obfuscated action and observation spaces.
Sample snippets of the dataset.
Top Submissions
Challenge Overview
You can find the baselines on Github.
The Task: Obtain Diamond in Minecraft
Minecraft is a 3D, first-person, open-world game centered around the gathering of resources and the creation of structures and items. These structures and items have prerequisite tools and materials required for their creation. As a result, many items require the completion of a series of natural subtasks.
The procedurally generated world is composed of discrete blocks that allow modification. Over the course of gameplay, players change their surroundings by gathering resources and constructing structures.
In this challenge, the goal is to obtain a diamond. The agent begins in a random starting location without any items and receives rewards for obtaining items which are prerequisites for diamond.
The stages of obtaining a diamond.
| Gather Wood |
Create Wood Pickaxe |
Mine Stone and Create Stone Pickaxe |
Mine Iron Ore |
|||
|---|---|---|---|---|---|---|
 |
 |
 |
|
 |
|
 |
| Create Furnace |
Smelt Iron and Create Iron Pickaxe |
Search | Mine Diamond |
|||
|---|---|---|---|---|---|---|
 |
|
 |
|
 |
|
 |
Citation
NeurIPS 2020 Competition: The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Mario Ynocente Castro, Sam Devlin, Brandon Houghton, Noboru Sean Kuno, Crissman Loomis, Keisuke Nakata, Stephanie Milani, Sharada Mohanty, Ruslan Salakhutdinov, Shinya Shiroshita, John Schulman, Nicholay Topin, Avinash Ummadisingu, Oriol Vinyals
NeurIPS 2020 Competition Track
2020
The MineRL Competition on Sample Efficient Reinforcement Learning using Human Priors
William H. Guss, Cayden Codel, Katja Hofmann, Brandon Houghton, Noboru Kuno, Stephanie Milani, Sharada Mohanty, Diego Perez Liebana, Ruslan Salakhutdinov, Nicholay Topin, Manuela Veloso, Phillip Wang
NeurIPS 2019 Competition Track
2019