The Emergence of Abstract and Episodic Neurons in Episodic Meta-RL

Abstract

In this work, we analyze the reinstatement mechanism introduced by Ritter et al. (2018) to reveal two classes of neurons that emerge in the agent's working memory (an epLSTM cell) when trained using episodic meta-RL on an episodic variant of the Harlow visual fixation task. Specifically, Abstract neurons encode knowledge shared across tasks, while Episodic neurons carry information relevant for a specific episode's task.

This work was accepted at the Learning to Learn Workshop (ICLR 2021)