Paper Info
Title
Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents
Abstract
ABSTRACT Critical periods are phases during which a toddler’s brain develops in spurts. To promote children’s cognitive development, proper guidance is critical in this stage. However, it is not clear whether such a critical period also exists for the training of AI agents. Similar to human toddlers, well-timed guidance and multimodal interactions might significantly enhance the training efficiency of AI agents as well. To validate this hypothesis, we adapt this notion of critical periods to learning in AI agents and investigate the critical period in the virtual environment for AI agents. We formalize the critical period and Toddler-guidance learning in the reinforcement learning (RL) framework. Then, we built up a toddler-like environment with VECA toolkit to mimic human toddlers’ learning characteristics. We study three discrete levels of mutual interaction: weak-mentor guidance (sparse reward), moderate mentor guidance (helper-reward), and mentor demonstration (behavioral cloning). We also introduce the EAVE dataset consisting of 30,000 real-world images to fully reflect the toddler’s viewpoint. We evaluate the impact of critical periods on AI agents from two perspectives: how and when they are guided best in both uni- and multimodal learning. Our experimental results show that both uni- and multimodal agents with moderate mentor guidance and critical period on 1 million and 2 million training steps show a noticeable improvement. We validate these results with transfer learning on the EAVE dataset and find the performance advancement on the same critical period and the guidance.
Year
DOI
Venue
2021
10.1145/3462244.3479932
ICMI-MLMI
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
7
Name
Order
Citations
PageRank
Junseok Park100.34
Kwanyoung Park200.68
Hyunseok Oh300.68
Ganghun Lee400.34
Min Su Lee500.34
Youngki Lee683270.33
Byoung-Tak Zhang700.34