Author name cluster

Youngjin Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2026 System Paper

RL-Studio: A System for Multi-Phase Reinforcement Learning Experimentation

Whiyoung Jung
Sunghoon Hong
Deunsol Yoon
Jeonghye Kim
Yongjae Shin
Suhyun Jung
Hyundam Yoo
Youngjin Kim

Reinforcement learning (RL) has evolved beyond monolithic training, yet existing frameworks remain limited to single algorithms or simple offline-to-online transitions. We present multi-phase RL, a framework that orchestrates multiple learning phases for continual policy improvement. It enables efficient fine-tuning of pretrained policies with new data and smooth adaptation from simulation to real-world environments. To support this paradigm, we introduce RL-Studio, a platform that addresses key implementation barriers, including neural architecture mismatches, parameter transfer complexities, and experiment management overhead. It provides phase orchestration, transition-point monitoring, and full experiment lineage tracking. We demonstrate the effectiveness of multi-phase RL through representative scenarios and highlight RL-Studio’s capabilities.

PDF Details DOI

IROS Conference 2023 Conference Paper

Kinematics-Only Differential Flatness Based Trajectory Tracking for Autonomous Racing

Yashom Dighe
Youngjin Kim
Smit Rajguru
Yash Turkar
Tarunraj Singh
Karthik Dantu

In autonomous racing, accurately tracking the race line at the limits of handling is essential to guarantee competitiveness. In this study, we show the effectiveness of Differential Flatness based control for high-speed trajectory tracking for car-like robots. We compare the tracking performance of our controller against Nonlinear Model Predictive Control and resource use while running on embedded hardware and show that on average KFC reduces the computation resource usage by 50 % while performing on par with NMPC. Our implementation of the proposed controller, the simulation environment and detailed results is open-sourced on https://github.com/droneslab/.

Details

ICML Conference 2019 Conference Paper

Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty

Youngjin Kim
Wontae Nam
Hyunwoo Kim 0002
Jihoon Kim
Gunhee Kim

Exploration based on state novelty has brought great success in challenging reinforcement learning problems with sparse rewards. However, existing novelty-based strategies become inefficient in real-world problems where observation contains not only task-dependent state novelty of our interest but also task-irrelevant information that should be ignored. We introduce an information- theoretic exploration strategy named Curiosity-Bottleneck that distills task-relevant information from observation. Based on the information bottleneck principle, our exploration bonus is quantified as the compressiveness of observation with respect to the learned representation of a compressive value network. With extensive experiments on static image classification, grid-world and three hard-exploration Atari games, we show that Curiosity-Bottleneck learns an effective exploration strategy by robustly measuring the state novelty in distractive environments where state-of-the-art exploration methods often degenerate.

Details

IROS Conference 2018 Conference Paper

A Novel Input Device for Robotic Prosthetic Hand: Design and Preliminary Results

Youngjin Kim
Dong-Hyuk Lee
Hyeonjun Park
Jae-Han Park
Ji-Hun Bae

In this paper, we propose a novel input device for a robotic prosthetic hand based on capacitance change. The proposed device can sense the deformation of the skin due to the activity of the muscle by measuring the capacitance change between the skin and the electrode. Therefore, it can be used as a sensor for estimating a user's intention through medical electrodiagnostic techniques such as electromyogram (EMG)and force myography (FMG). The proposed device can acquire data in a non-invasive way and is advantageous with easier data processing than that for an EMG signal. Moreover, it is resistant to the impedance change of skin because the capacitance is measured in a non-contact manner, unlike the existing methods which work with direct contact with the skin such as EMG. Additionally, unlike FMG, the device is lightly attached to the skin without being strongly fixed with velcro, which offsets problems that occur while re-wearing the device. To demonstrate the feasibility of the proposed idea, three of the newly developed input devices were used to classify four hand movements (fist, scissors, paper, and rest)using a multilayer perceptron (MLP). As a result, the classification success rates for the fist, paper, scissor, and rest motions were obtained as 99. 3%, 98. 3%, 98. 4%, and 99. 1%, respectively.

Details