Reinforcement Learning, Fast and Slow
In Meta-RL: establish inductive biases that can guide inference and thus support rapid adaptation to new tasks In Episodic RL: Episodic RL inherently depends on judgments concerning resemblances between situations or states. Slow learning shapes the way that states are internally represented and thus puts in place a set of inductive biases concerning which states are most closely related. 真に汎用な学習アルゴリズムではなく，周囲の環境のregularitiesを活用するアルゴリズムを選択する REVIEW | VOLUME 23, ISSUE 5, P408-422, MAY 01, 2019
Published: April 16, 2019