ByungSunBae

# Thanks for 주찬웅
# References:
## 1) https://github.com/jcwleo/Reinforcement_Learning/blob/master/Breakout/
## 2) http://pytorch.org/tutorials/ 
## 3) https://github.com/transedward/pytorch-dqn

## My codes is very very dirty...
## I want to your idea and advice that improves this codes.

import argparse

ByungSunBae

DRL : Policy Gradient

Overview

• Deep Q network(이하 DQN)와 그 Variants(DoubleDQN, DuelingDQN)를 구현해보았다.

---

• 그런데 DQN과 같은 계열의 방법은 RL에서 Value-Based Method라서 Policy에 대한 직접적인 학습이 아니다.

• 게다가 Value가 약간만 바뀌어도 Policy가 금방 변한다.

• 학습과정이 불안정하게되어 수렴자체가 불안정해진다. (Bias가 높다.)

ByungSunBae

# 2) RNN model 생성----------------
## Refer : https://github.com/hunkim/DeepLearningZeroToAll/blob/master/lab-12-5-rnn_stock_prediction.py
library(tensorflow)
library(reticulate)

contrib <- tf$contrib

tf$reset_default_graph()

# train Parameters

ByungSunBae

## Convex Optimization in R using CVXR
## from : https://rviews.rstudio.com/2017/11/27/introduction-to-cvxr/

## load CVXR
if (!require(CVXR)){
  install.packages("CVXR")
} else{
  require(CVXR)
}

ByungSunBae

# from : https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/graph_editor/examples/edit_graph_example.py
import numpy as np

import tensorflow as tf
from tensorflow.contrib import graph_editor as ge

# create a graph
g = tf.Graph()

with g.as_default():

ByungSunBae

# References:

import argparse

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.autograd import Variable
import torchvision.transforms as T

ByungSunBae

import tensorflow as tf
from tensorflow import layers
from tensorflow.contrib.layers import xavier_initializer

import gym
import numpy as np

from collections import deque
from collections import namedtuple

ByungSunBae

# 스타워즈 시리즈들의 유사도를 등장인물들을 통해 계산하고 시각화 하는 문제
# From : https://github.com/R-Korea/weekly_R_quiz/blob/master/201808/1.movie_similarity/movie_similarity_quiz.Rmd
library(dplyr)
library(data.table)
library(ggplot2)
library(scales)

rm(list=ls())

raw.data <- 

ByungSunBae

// From : https://www.edwith.org/datascience/lecture/33888/
// edwith에서 한글자막을 달아놓은 MIT의 Data Science 강좌중 첫번째 챕터입니다.
// 위 링크에서 파이썬 버전의 코드를 받아보실 수 있습니다.
// 칼로리가 제한될 때, 음식을 선택하는 문제를 탐욕 알고리즘으로 푸는 문제입니다.
// 파이썬 코드를 Golang으로 변환했습니다.

package main

import (
	"flag"

ByungSunBae

package main

import (
        "fmt"
        "github.com/kniren/gota/dataframe"
        tf "github.com/tensorflow/tensorflow/tensorflow/go"
        "github.com/tensorflow/tensorflow/tensorflow/go/op"
        "os"
)