Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Complex feedback in online learning

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

Junseok Park · Inwoo Hwang · Min Whoo Lee · Hyunseok Oh · Minsu Lee · Youngki Lee · Byoung-Tak Zhang


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 faping 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.

Chat is not available.