Difference between r1.47 and the current
@@ -1,14 +1,15 @@
[[Tableofcontents]]
= machine learning =
1. Unsupervised learning
1. Reinforcement learning
== supervised learning ==
== unsupervised learning ==
* Human can't predict the outcome
* e.g. clustering
= machine learning =
머신 러닝의 세가지 분류
1. Supervised learning1. Unsupervised learning
1. Reinforcement learning
== supervised learning ==
* 학습을 시킬 때 input으로 value와 label을 함께 전달
* Learning from difference between prediction and target
* 학습을 시킬 때 input으로 feature(입력값)와 label(원하는 결과값)을 함께 전달
* Learning from difference between prediction and label
* e.g. mnist, classification== unsupervised learning ==
* input: value만 입력, projection등으로 전처리한 값들로 계산
* input: feature만 입력, 보통 projection등으로 feature의 차원을 축소시킨다.
* Cluster by distance between inputs* Human can't predict the outcome
* e.g. clustering
@@ -16,7 +17,7 @@
* 일종의 unsupervised learning
* input : environment, reward, output : action
* Learn from try
* Model free
== reinforcement learning ==
* Q learning
* input : environment, reward, output : action
* Learn from try
* Model free: 게임의 규칙을 알려주지 않음
* e.g. game play, stock trading== reinforcement learning ==
* Q learning
@@ -32,27 +33,28 @@
* Value iteration, Polish iteration
== 실습 ==
* [https://github.com/openai/gym in github]
* 필요한 라이브러리: numpy, gym, tensorflow 필요
{{{
$ pip install gym
$ pip install tensorflow
}}}
1. q-network(q-learning의 NN버전) - [https://github.com/Rabierre/cartpole/blob/master/cartpole_qnetwork.py cartpole_qnetwork.py]
* 발표 슬라이드: [https://slides.com/rabierre/playing_a_game_with_rl slide]
== Furthermore ==
* [https://en.wikipedia.org/wiki/David_Silver_(programmer) David Silver]의 강의
* [http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html 강의노트]
* [https://www.youtube.com/watch?v=2pWv7GOvuf0 강의 영상]
== 실습 ==
* [https://gym.openai.com gym]: Reinforcement learning을 위한 고전 게임들을 python으로 포팅한 toolkit. 직접 구현한 것도 있고 atari는 포팅함.
* [https://gym.openai.com gym]: Reinforcement learning을 위한 고전 게임들을 python으로 포팅한 toolkit. 직접 구현한 것도 있고 atari는 포팅함. [https://github.com/openai/gym github]에 코드가 공개되어 있다.
* 오늘 실습할 [https://gym.openai.com/envs/CartPole-v0 cartpole]{{{
$ pip install gym
$ pip install tensorflow
}}}
1. cartpole 실행을 해보자! - [https://github.com/Rabierre/cartpole/blob/master/cartpole_init.py cartpole_init.py]
=== 순서 ===
1. 일단 cartpole 실행을 해보자! - [https://github.com/Rabierre/cartpole/blob/master/cartpole_init.py cartpole_init.py]
1. random action(왼쪽, 오른쪽)을 하는 cartpole - [https://github.com/Rabierre/cartpole/blob/master/cartpole_random.py cartpole_random.py]1. q-network(q-learning의 NN버전) - [https://github.com/Rabierre/cartpole/blob/master/cartpole_qnetwork.py cartpole_qnetwork.py]
1. DQN - cartpole_dqn.py
1. 2015에 Deep Mind에서 발표한 DQN - cartpole_dqn2015.py
1. DQN - [https://github.com/Rabierre/cartpole/blob/master/cartpole_dqn.py cartpole_dqn.py]
1. 2015에 Deep Mind에서 발표한 DQN - [https://github.com/Rabierre/cartpole/blob/master/cartpole_dqn2015.py cartpole_dqn2015.py]
== Reference ==* 발표 슬라이드: [https://slides.com/rabierre/playing_a_game_with_rl slide]
* 코드: [https://github.com/Rabierre/cartpole github]
* 논문: [https://arxiv.org/abs/1312.5602 Playing Atari with Deep Reinforcement Learning]
* 실습코드: [https://github.com/Rabierre/cartpole github]
* DeepMind의 DQN 논문: [https://arxiv.org/abs/1312.5602 Playing Atari with Deep Reinforcement Learning]
* Tensorflow tutorial: [https://github.com/golbin/TensorFlow-Tutorials/tree/master/10%20-%20DQN DQN]== Furthermore ==
* [https://en.wikipedia.org/wiki/David_Silver_(programmer) David Silver]의 강의
* [http://www0.cs.ucl.ac.uk/staff/d.silver/web/Teaching.html 강의노트]
* [https://www.youtube.com/watch?v=2pWv7GOvuf0 강의 영상]
* Gitbook: [https://www.gitbook.com/book/dnddnjs/rl/details Fundamental of Reinforcement Learning]
== 하고싶은 말 ==
* Gitbook: [https://www.gitbook.com/book/dnddnjs/rl/details Fundamental of Reinforcement Learning]. 한글로 되어 있다!
* 레퍼런스 모음: [Machine%20Learning]
== 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
- 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!
- 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
1.6.1. 순서 ¶
- 일단 cartpole 실행을 해보자! - cartpole_init.py
- random action(왼쪽, 오른쪽)을 하는 cartpole - cartpole_random.py
- q-network(q-learning의 NN버전) - cartpole_qnetwork.py
- DQN - cartpole_dqn.py
- 2015에 Deep Mind에서 발표한 DQN - cartpole_dqn2015.py
1.7. Reference ¶
- 발표 슬라이드: slide
- 실습코드: github
- DeepMind의 DQN 논문: Playing Atari with Deep Reinforcement Learning
- Tensorflow tutorial: DQN
1.8. Furthermore ¶
- David Silver의 강의
- Gitbook: Fundamental of Reinforcement Learning. 한글로 되어 있다!
- 레퍼런스 모음: Machine%20Learning
