On the Importance of Critical Period in Multi-stage Reinforcement Learning

The initial years of an infant's life are known as the critical period, during which the overall development of learning performance is significantly impacted due to neural plasticity. In recent studies, an AI agent, with a deep neural network mimicking mechanisms of actual neurons, exhibited a...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Park, Junseok, Hwang, Inwoo, Lee, Min Whoo, Oh, Hyunseok, Lee, Minsu, Lee, Youngki, Byoung-Tak Zhang
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 09.08.2022
Subjects
Artificial neural networks
Human bias
Human performance
Machine learning
Online AccessGet full text

Cover

More Information
Summary:The initial years of an infant's life are known as the critical period, during which the overall development of learning performance is significantly impacted due to neural plasticity. In recent studies, an AI agent, with a deep neural network mimicking mechanisms of actual neurons, exhibited a learning period similar to human's critical period. Especially during this initial period, the appropriate stimuli play a vital role in developing learning ability. However, transforming human cognitive bias into an appropriate shaping reward is quite challenging, and prior works on critical period do not focus on finding the appropriate stimulus. To take a step further, we propose multi-stage reinforcement learning to emphasize finding ``appropriate stimulus" around the critical period. Inspired by humans' early cognitive-developmental stage, we use multi-stage guidance near the critical period, and demonstrate the appropriate shaping reward (stage-2 guidance) in terms of the AI agent's performance, efficiency, and stability.
ISSN:2331-8422