MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned

TL;DR

The MineRL Diamond 2021 competition aimed to promote generalizable, sample-efficient reinforcement learning solutions by hosting both challenging and accessible tracks, increasing participation and advancing the field.

Contribution

This paper presents the overview, results, and lessons learned from the third MineRL Diamond competition, including the introduction of an easier track to encourage broader participation.

Findings

Increased submissions due to an accessible track

Participants achieved diamond in the easier track

Progress made in generalizable solutions for the task

Abstract

Reinforcement learning competitions advance the field by providing appropriate scope and support to develop solutions toward a specific problem. To promote the development of more broadly applicable methods, organizers need to enforce the use of general techniques, the use of sample-efficient methods, and the reproducibility of the results. While beneficial for the research community, these restrictions come at a cost -- increased difficulty. If the barrier for entry is too high, many potential participants are demoralized. With this in mind, we hosted the third edition of the MineRL ObtainDiamond competition, MineRL Diamond 2021, with a separate track in which we permitted any solution to promote the participation of newcomers. With this track and more extensive tutorials and support, we saw an increased number of submissions. The participants of this easier track were able to obtain a diamond, and the participants of the harder track progressed the generalizable solutions in the same task.