On the Importance of Critical Period in Multi-stage Reinforcement Learning
Abstract
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.
Keywords
Cite
@article{arxiv.2208.04832,
title = {On the Importance of Critical Period in Multi-stage Reinforcement Learning},
author = {Junseok Park and Inwoo Hwang and Min Whoo Lee and Hyunseok Oh and Minsu Lee and Youngki Lee and Byoung-Tak Zhang},
journal= {arXiv preprint arXiv:2208.04832},
year = {2022}
}
Comments
Accepted by the ICML Complex Feedback in Online Learning Workshop (Open Problems) 2022