Jihwan Lee

Ph.D. Student, AI Graduate School, GIST

me.jpg

AI Graduate School, GIST

Gwangju, South Korea

jihwan.lee@gm.gist.ac.kr

I am a Ph.D. student in the AI Graduate School at GIST, advised by Prof. Sundong Kim. My research is in reinforcement learning, with a focus on building agents that adapt efficiently across diverse tasks and environments.

I am interested in world models, temporal abstraction, and how agents can extract and generalize reusable knowledge to make robust decisions in new settings.

publications

  1. ICML DEMO Workshop
    Receding-Horizon Execution for Action Chunking in Offline-to-Online Reinforcement Learning
    Jihwan Lee, Geonwoo Cho, Hojun Yi, and 3 more authors
    In Decision-Making from Offline Datasets to Online Adaptation: Black-Box Optimization to Reinforcement Learning, 2026
    HTML
  2. ICLR
    AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
    Geonwoo Cho, Jaemoon Lee, Jaegyun Im, and 3 more authors
    In The Fourteenth International Conference on Learning Representations, 2026
    HTML
  3. ICLR
    TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
    Geonwoo Cho, Jaegyun Im, Jihwan Lee, and 3 more authors
    In The Fourteenth International Conference on Learning Representations, 2026
    HTML
  4. IARML@IJCAI
    Enhancing Analogical Reasoning in the Abstraction and Reasoning Corpus via Model-Based RL
    Jihwan Lee, Woochang Sim, Sejin Kim, and 1 more author
    In IJCAI Workshop on Interdisciplinary Approaches to Reasoning with Machine Learning (IARML), Aug 2024
    HTML
  5. CoLLAs
    ARCLE: The Abstraction and Reasoning Corpus Learning Environment for Reinforcement Learning
    Hosung Lee, Sejin Kim, Seungpil Lee, and 4 more authors
    In Conference on Lifelong Learning Agents (CoLLAs), Jan 2024
    HTML
  6. KSC
    Extracting the Core Knowledge of ARC with the World Model
    Jihwan Lee, Seungpil Lee, Sejin Kim, and 1 more author
    In Korea Software Congress (KSC), Dec 2023
  7. KSC
    Evaluating Prior Knowledge of ARC Using World Models
    Seungpil Lee, Jihwan Lee, and Sundong Kim
    In Korea Software Congress (KSC), Dec 2023