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

Badr AlKhamissi, Muhammad ElNokrashy, Michael Spranger

Keywords: Meta-RL, Episodic Meta-RL, Neuroscience

TL;DR: Analysis of the reinstatement gate activations in episodic meta-reinforcement learning.

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.

Proposed Reviewers:

Badr AlKhamissi, [e-mail]
Muhammed ElNokrashy, [e-mail]

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2104.02959/code)