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

04/07/2021
by   Badr AlKhamissi, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2019

Meta Reinforcement Learning with Task Embedding and Shared Policy

Despite significant progress, deep reinforcement learning (RL) suffers f...
research
05/03/2019

Meta-learners' learning dynamics are unlike learners'

Meta-learning is a tool that allows us to build sample-efficient learnin...
research
11/02/2020

Information-theoretic Task Selection for Meta-Reinforcement Learning

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of...
research
12/28/2017

Rapid Adaptation with Conditionally Shifted Neurons

We describe a mechanism by which artificial neural networks can learn ra...
research
12/14/2021

How to Learn and Represent Abstractions: An Investigation using Symbolic Alchemy

Alchemy is a new meta-learning environment rich enough to contain intere...
research
12/02/2019

TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP

While state-of-the-art NLP explainability (XAI) methods focus on supervi...
research
06/14/1999

Ocular dominance patterns in mammalian visual cortex: A wire length minimization approach

We propose a theory for ocular dominance (OD) patterns in mammalian prim...

Please sign up or login with your details

Forgot password? Click here to reset