Contents

1. machine learning

1.1. supervised learning

1.2. unsupervised learning

1.3. reinforcement learning

1.4. reinforcement learning

1.5. Basic knowledge

1.6. 실습

1.6.1. 순서

1.7. Reference

1.8. Furthermore

1.9. 후기 및 기타의견

1. machine learning ¶

머신 러닝의 세가지 분류

Supervised learning
Unsupervised learning
Reinforcement learning

1.1. supervised learning ¶

학습을 시킬 때 input으로 feature(입력값)와 label(원하는 결과값)을 함께 전달
Learning from difference between prediction and label
e.g. mnist, classification

1.2. unsupervised learning ¶

input: feature만 입력, 보통 projection등으로 feature의 차원을 축소시킨다.
Cluster by distance between inputs
Human can't predict the outcome
e.g. clustering

1.3. reinforcement learning ¶

일종의 unsupervised learning
input : environment, reward, output : action
Learn from try
- Model free: 게임의 규칙을 알려주지 않음
e.g. game play, stock trading

1.4. reinforcement learning ¶

Q learning
Q learning + Neural Network
DQN : Deep Q Learning
- hidden layer를 늘리는게 다가 아니다!

1.5. Basic knowledge ¶

MDP : Markov Decision Process
Bellman equation
Dynamic programming
Value, Polish
Value function, Polish function
Value iteration, Polish iteration

1.6. 실습 ¶

gym(https://gym.openai.com): Reinforcement learning을 위한 고전 게임들을 python으로 포팅한 toolkit. 직접 구현한 것도 있고 atari는 포팅함. github(https://github.com/openai/gym)에 코드가 공개되어 있다.
- 오늘 실습할 cartpole(https://gym.openai.com/envs/CartPole-v0)
필요한 라이브러리: numpy, gym, tensorflow 필요
```
  $ pip install gym
  $ pip install tensorflow 
```

1.6.1. 순서 ¶

일단 cartpole 실행을 해보자! - cartpole_init.py(https://github.com/Rabierre/cartpole/blob/master/cartpole_init.py)
random action(왼쪽, 오른쪽)을 하는 cartpole - cartpole_random.py(https://github.com/Rabierre/cartpole/blob/master/cartpole_random.py)
q-network(q-learning의 NN버전) - cartpole_qnetwork.py(https://github.com/Rabierre/cartpole/blob/master/cartpole_qnetwork.py)
DQN - cartpole_dqn.py(https://github.com/Rabierre/cartpole/blob/master/cartpole_dqn.py)
2015에 Deep Mind에서 발표한 DQN - cartpole_dqn2015.py(https://github.com/Rabierre/cartpole/blob/master/cartpole_dqn2015.py)

1.7. Reference ¶

발표 슬라이드: slide(https://slides.com/rabierre/playing_a_game_with_rl)
실습코드: github(https://github.com/Rabierre/cartpole)
DeepMind의 DQN 논문: Playing Atari with Deep Reinforcement Learning(https://arxiv.org/abs/1312.5602)
Tensorflow tutorial: DQN(https://github.com/golbin/TensorFlow-Tutorials/tree/master/10%20-%20DQN)

1.8. Furthermore ¶

David Silver(https://en.wikipedia.org/wiki/David_Silver_(programmer))의 강의
- 강의노트(http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html)
- 강의 영상(https://www.youtube.com/watch?v=2pWv7GOvuf0)
Gitbook: Fundamental of Reinforcement Learning(https://www.gitbook.com/book/dnddnjs/rl/details). 한글로 되어 있다!
레퍼런스 모음: Machine%20Learning

1.9. 후기 및 기타의견 ¶

Retrieved from http://wiki.zeropage.org/wiki.php/데블스캠프2017/강화학습으로컴퓨터에게고전게임플레이시키기
last modified 2021-02-07 05:29:18