階層型強化学習arXiv:1805.08180
後知恵学習を用いた階層型強化学習
Hierarchical Reinforcement Learning with Hindsight
遅延・疎な報酬環境で、複数の時間スケールの行動を並列に学習する階層型強化学習手法を提案し、サンプル効率を大幅に改善した。
著者: Andrew Levy, Robert Platt, Kate Saenko
分類: cs.LG, cs.AI, cs.NE, cs.RO, stat.ML
原文アブストラクト
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functions and hindsight learning, allowing agents to learn policies belonging to different time scales in parallel. We show that our method significantly accelerates learning in a variety of discrete and continuous tasks.
