SEIHAI: サンプル効率の高い階層型AIによるMineRL競技への挑戦
SEIHAI: A Sample-efficient Hierarchical AI for the MineRL Competition
MineRLのObtainDiamondタスクを、人間のデモンストレーションを活用してタスクを逐次的なサブタスクに分割し、強化学習と模倣学習で各エージェントを訓練、スケジューラで自動選択する階層型AIを提案し、NeurIPS-2020 MineRL競技で優勝した。
著者: Hangyu Mao, Chao Wang, Xiaotian Hao, Yihuan Mao, Yiming Lu, Chengjie Wu, Jianye Hao, Dong Li, Pingzhong Tang
分類: cs.LG, cs.AI, cs.MA, cs.RO, cs.SY, eess.SY
原文アブストラクト
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.
