Retrospective Analysis of the 2019 MineRL Competition on Sample Efficient Reinforcement Learning

Abstract

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.

arXiv commentTo appear in Proceedings of Machine Learning Research: NeurIPS 2019 Competition & Demonstration Track Postproceedings. 12 pages, 2 figures

References in corpus (15)

• Rainbow: Combining Improvements in Deep Reinforcement Learning
• Control of Memory, Active Perception, and Action in Minecraft
• A Deep Hierarchical Approach to Lifelong Learning in Minecraft
• Investigating Human Priors for Playing Video Games
• Gotta Learn Fast: A New Benchmark for Generalization in RL
• ChainerRL: A Deep Reinforcement Learning Library
• The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition
• The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors
• Deep Reinforcement Learning from Policy-Dependent Human Feedback
• Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains
• The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors
• Sample Efficient Reinforcement Learning through Learning from Demonstrations in Minecraft
• Playing Minecraft with Behavioural Cloning
• Guaranteeing Reproducibility in Deep Learning Competitions
• Improving Deep Reinforcement Learning in Minecraft with Action Advice

Cited by in corpus (1)

• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory