TLTaeho Lee

Taeho Lee

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Taeho Lee has a total of 7 co-authors. Here are the top co-authors by number of shared publications:

  • Donghwan Lee

    Korea Advanced Institute of Science and Technology

    2 shared publications
  • Bumgeun Park

    School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Yuseong-gu, Daejeon, Republic of Korea

    1 shared publication
  • Heechan Chung

    Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

    1 shared publication
  • Hyungjun Kim

    AI Perceived Quality Research Team, Future Network Laboratory, Network Group, KT Research and Development Center, Seoul, Republic of Korea

    1 shared publication
  • Jongchan Park

    School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

    1 shared publication
  • Tae-Young Kim

    AI Security Research Team, Future Network Laboratory, Network Group, KT Research and Development Center, Seoul, Republic of Korea

    1 shared publication

Latest Publications

  • Open Access

    Deep Q-Learning With Gradient Target Tracking

    by Bumgeun Park, Taeho Lee, Donghwan Lee

    This paper introduces Q-learning with gradient target tracking, a novel reinforcement learning framework that provides a learned continuous target update mechanism as an alternative to the conventional hard update paradigm. In the standard deep Q-network (DQN), the target network is a copy of the online network’s weights, held fixed for a number of iterations before being periodically replaced via a hard update. While this stabilizes training by providing consistent targets, it introduces a new challenge: the hard update period must be carefully tuned to achieve optimal performance. To address this issue, we propose two gradient-based target update methods: DQN with asymmetric gradient target tracking (AGT2-DQN) and DQN with symmetric gradient target tracking (SGT2-DQN). These methods replace the conventional hard target updates with continuous and structured updates using gradient descent, which effectively eliminates the need for manual tuning. We provide a theoretical analysis proving the convergence of these methods in tabular settings. Additionally, empirical evaluations demonstrate their advantages over standard DQN baselines, which suggest that gradient-based target updates can serve as an effective alternative to conventional target update mechanisms in Q-learning.

  • Open Access

    Power Consumption Optimization of GPU Server With Offline Reinforcement Learning

    by Heechan Chung, Yeeun Im, Jongchan Park, Taeho Lee, Tae-Young Kim, Hyungjun Kim, Donghwan Lee

    The rapid growth of artificial intelligence (AI) has led to increased reliance on power-intensive Graphics Processing Units (GPUs), which are essential for training and deploying large-scale models. However, the escalating energy demands of AI workloads pose sustainability challenges, necessitating efficient power management strategies to reduce carbon footprints. Optimizing GPU server power consumption is complex due to the interdependence of various components. Conventional methods often involve trade-offs: increasing fan speed enhances cooling but raises overall power usage, whereas lowering GPU clock frequencies conserves energy at the cost of longer computation times. To address these challenges, we propose a data-driven optimization framework based on offline reinforcement learning (RL). Our approach collects operational data from a custom-designed workload that simulates varying server loads, capturing key metrics such as power consumption, temperature, and core frequency. The reward function balances power efficiency with performance. The reinforcement learning agent learns from pre-collected server logs, enabling intelligent real-time GPU clock control decisions without costly live experiments. Additionally, periodic fan speed adjustments and pre-training of the Q-network further enhance overall efficiency. Experimental results demonstrate that our method reduces power consumption by 3.62% while improving computation time by 1.51% for synthetic workloads. For LLaMA-2 fine-tuning, power consumption decreases by 6.40% with only a minor 1.27% increase in computation time, demonstrating its practical effectiveness. Our framework was validated on the latest NVIDIA L40S GPU, demonstrating its compatibility with cutting-edge hardware.