Skip to content
View DevSlem's full-sized avatar
20 followers · 15 following

Achievements

Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Achievements

Achievement: YOLOAchievement: Pull Sharkx2Achievement: Quickdraw

Highlights

  • Pro

Organizations

@Team-UGD @CS-PingPing @ComPPing
Block or Report

Block or report DevSlem

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DevSlem/README.md

Profile 👋

University - Incheon National University
Blog - DevSlem Blog
E-mail - [email protected]
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

Tech Stack


Field

  • Reinforcement Learning (RL) 🔥
  • Machine Learning

Project

  • Back to the Dungeon: Unity 2D Platformer Shooting Game
  • AINE-DRL: Deep Reinforcement Learning Baseline Framework
  • Mol-AIR: Molecular Reinforcement Learning with Adaptive Intrinsic Reward for Goal-directed Molecular Generation
  • Multiple Knapsack: Multiple Knapsack Optimization using Deep Reinforcement Learning with Transformer

Pinned Loading

  1. Mol-AIR Mol-AIR Public

    Molecular Reinforcement Learning with Adaptive Intrinsic Reward for Goal-directed Molecular Generation.

    Python 2 1

  2. multiple-knapsack multiple-knapsack Public

    Optimize multiple knapsack problem using reinforcement learning.

    Python 1

  3. AINE-DRL AINE-DRL Public

    AINE-DRL is a deep reinforcement learning (DRL) baseline framework. AINE means "Agent IN Environment".

    Python 7 2

  4. unity-move-tool unity-move-tool Public

    Unity editor position handle utility for the fields like Vector3, not GameObject.

    C# 9 1

  5. Team-UGD/back-to-the-dungeon-scripts Team-UGD/back-to-the-dungeon-scripts Public

    We share scripts used for "Back to The Dungeon" project.

    C# 2 2