Title | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2022 | 10.24963/ijcai.2022/452 | European Conference on Artificial Intelligence |
Keywords | DocType | Citations |
Machine Learning: Deep Reinforcement Learning,Search: Game Playing | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zichuan Lin | 1 | 4 | 3.22 |
Junyou Li | 2 | 0 | 0.68 |
Jianing Shi | 3 | 0 | 1.01 |
Deheng Ye | 4 | 105 | 8.89 |
Qiang Fu | 5 | 1 | 4.42 |
Wei Yang | 6 | 93 | 27.50 |