JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning
Abstract
Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration. Specifically, our approach includes two levels of hierarchy, where the high-level controller learns a policy to control over options and the low-level workers learn to solve each sub-task. To boost the learning of sub-tasks, we propose a combination of techniques including 1) action-aware representation learning which captures underlying relations between action and representation, 2) discriminator-based self-imitation learning for efficient exploration, and 3) ensemble behavior cloning with consistency filtering for policy robustness. Extensive experiments show that JueWu-MC significantly improves sample efficiency and outperforms a set of baselines by a large margin. Notably, we won the championship of the NeurIPS MineRL 2021 research competition and achieved the highest performance score ever.
Cite
@article{arxiv.2112.04907,
title = {JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning},
author = {Zichuan Lin and Junyou Li and Jianing Shi and Deheng Ye and Qiang Fu and Wei Yang},
journal= {arXiv preprint arXiv:2112.04907},
year = {2021}
}
Comments
The champion solution of NeurIPS 2021 MineRL research competition ( https://www.aicrowd.com/challenges/neurips-2021-minerl-diamond-competition/leaderboards )