← Search

Mingyu Park

2 accepted papers

2025

Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning

NeurIPS 2025poster

Offline reinforcement learning (RL) aims to learn a policy from a fixed dataset without additional environment interaction. However, effective offline policy learning often requires a large and diverse dataset to mitigate epistemic uncertainty. Collecting such data demands substantial online interac…

Cited by 0SourceScholar
2022

Infusing Model Predictive Control Into Meta-Reinforcement Learning for Mobile Robots in Dynamic Environments

RA-L 2022

The successful operation of mobile robots requires them to adapt rapidly to environmental changes. To develop an adaptive decision-making tool for mobile robots, we propose a novel algorithm that combines meta-reinforcement learning (meta-RL) with model predictive control (MPC). Our method employs a

Cited by 15SourcecodeScholar