Hi, I'm an AI researcher interested in deep learning and reinforcement learning. Feel free to see my projects and contact me.
University - Incheon National University
Blog - DevSlem Blog
E-mail - devslem12@gmail.com
LinkedIn - Jinyeong Park
Optimize my daily routine using reinforcement learning (Q-learning):
# take a step S = "busy" # state A = "play" in { "play", "work" } # action S' = "boom" # next state R = -100 # penalty # learn from the experience Q[S,A] += alpha * (R + gamma * max(Q[S',:]) - Q[S,A]) # but, still I don't want to work... A' = "play" # next action
| Title (Year) β¬οΈ | Category | Available Sources | Description |
|---|---|---|---|
| Mol-AIR (2025) | RL, Drug Design | Repository / Paper | Molecular reinforcement learning with adaptive intrinsic reward for goal-directed molecular generation |
| Multiple Knapsack (2024) | RL, Combinatorial | Repository | Comprehensive comparison of RL methods for the multiple knapsack problem |
| AINE-DRL (2023) | RL, Utility | Repository / Download | Deep reinforcement learning baseline framework |
| Move-Tool (2022) | Unity, Utility | Repository | Unity editor position handle utility for the vector-like fields |
| Back to the Dungeon (2022) | Unity, Game | Repository / Download | Unity 2D platformer shooting game |