The MineRL competition is designed for the development of reinforcement learning and imitation learning algorithms that can efficiently leverage human demonstrations to drastically reduce the number of environment interactions needed to solve the complex \emph{ObtainDiamond} task with sparse rewards. To address the challenge, in this paper, we present \textbf{SEIHAI}, a \textbf{S}ample-\textbf{e}ff\textbf{i}cient \textbf{H}ierarchical \textbf{AI}, that fully takes advantage of the human demonstrations and the task structure. Specifically, we split the task into several sequentially dependent subtasks, and train a suitable agent for each subtask using reinforcement learning and imitation learning. We further design a scheduler to select different agents for different subtasks automatically. SEIHAI takes the first place in the preliminary and final of the NeurIPS-2020 MineRL competition.
@article{arxiv.2111.08857,
title = {SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition},
author = {Hangyu Mao and Chao Wang and Xiaotian Hao and Yihuan Mao and Yiming Lu and Chengjie Wu and Jianye Hao and Dong Li and Pingzhong Tang},
journal= {arXiv preprint arXiv:2111.08857},
year = {2021}
}
Comments
The winner solution of NeurIPS 2020 MineRL competition (https://www.aicrowd.com/challenges/neurips-2020-minerl-competition/leaderboards). The paper has been accepted by DAI 2021 (the third International Conference on Distributed Artificial Intelligence)