There's a version of this question specifically referring to obtaining a diamond through mining (as opposed to finding it in e.g. a shipwreck or treasure chest)
Abstract
Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples. Many of these systems cannot be applied to real-world problems, where environment samples are expensive. Resolution of these limitations requires new, sample-efficient methods.
This competition is designed to foster the development of algorithms which can drastically reduce the number of samples needed to solve complex, hierarchical, and sparse environments using human demonstrations. Participants compete to develop systems which solve a hard task in Minecraft, obtaining a diamond, with a limited number of samples.
Resolution
This question will resolve positively if a Minecraft RL agent that competes in the competition, successfully secures a diamond before the end of the competition.
Note that Training in the competition is limited to a single instance with a wall clock time of 4 days (96 hours).
Note: The Minecraft RL agent must be one that is deemed appropriate to compete by the judges (i.e. not a hardcoded solution)