Seunghwa back's repositories
Coding-Test
코테 준비 practice on coding test
Language:Python000
de-git
data engineering test
000
DeepLearningZeroToAll
TensorFlow Basic Tutorial Labs
Language:Jupyter Notebook000
kaggle
캐글 대회 참가 기록 kaggle competition
Language:Jupyter Notebook000
Multi-Armed-Bandit
MAB 구현 연습
Language:Python000
Project
머신 러닝 및 딥러닝 모델 구현
Language:Jupyter Notebook000
Reinforcement-Learning
Implemented Reinforcement Learning Algorithm in Python. The two TD Learning algorithms used were SARSA and Q Learning. SARSA was used for implementing Maze Problem whereas Q-Learning was used for implementing Blackjack Game. Used gym toolkit of Python.
Language:Jupyter Notebook000
Yahoo_recommendation
Yahoo! news article recommendation system by linUCB
Language:Python000