Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning
This competition addressed the problem of sample inefficiency in reinforcement learning for researchers, though it was incremental as it built on existing competition frameworks.
The authors organized the 2019 MineRL competition to promote sample-efficient reinforcement learning algorithms using human demonstrations, resulting in top solutions employing deep reinforcement learning and imitation learning.
To facilitate research in the direction of sample efficient reinforcement learning, we held the MineRL Competition on Sample Efficient Reinforcement Learning Using Human Priors at the Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019). The primary goal of this competition was to promote the development of algorithms that use human demonstrations alongside reinforcement learning to reduce the number of samples needed to solve complex, hierarchical, and sparse environments. We describe the competition, outlining the primary challenge, the competition design, and the resources that we provided to the participants. We provide an overview of the top solutions, each of which use deep reinforcement learning and/or imitation learning. We also discuss the impact of our organizational decisions on the competition and future directions for improvement.