Min Whoo Lee — accepted AI-conference papers

2024

Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning

Junseok Park, Yoonsung Kim, Hee bin Yoo, Min Whoo Lee, Kibeom Kim, Won-Seok Choi +2

AAAI 2024technical

Toddlers evolve from free exploration with sparse feedback to exploiting prior experiences for goal-directed learning with denser rewards. Drawing inspiration from this Toddler-Inspired Reward Transition, we set out to explore the implications of varying reward transitions when incorporated into Rei…

Cited by 3 Source ↗PDF ↗Scholar ↗

2021

Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning

Kibeom Kim, Min Whoo Lee, Yoonsung Kim, JeHwan Ryu, Minsu Lee, Byoung-Tak Zhang

NeurIPS 2021poster

Learning in a multi-target environment without prior knowledge about the targets requires a large amount of samples and makes generalization difficult. To solve this problem, it is important to be able to discriminate targets through semantic understanding. In this paper, we propose goal-aware cross…

Cited by 11 Source ↗PDF ↗code ↗Scholar ↗