kkweon

"""
Deep Deterministic Policy Gradients (DDPG)
https://arxiv.org/pdf/1509.02971.pdf

TODO: Batch Normalization Bug
"""
import argparse
import random
import numpy as np
import gym

kkweon

kkweon

"""
Simple implemntation of
"Efficient Parallel Methods for Deep Reinforcement Learning"
https://arxiv.org/abs/1705.04862

"""
import argparse
import tensorflow as tf
import numpy as np
import gym

kkweon

library(ggplot2)

secant <- function(fn) {
    a <- -100
    b <- 100
    for (i in 1:1000) {
        numerator <- b * fn(a) - a * fn(b)
        denominator <- fn(a) - fn(b) + 1e-9
        x <- numerator / denominator
        a <- b

kkweon

"""Simple example on how to log scalars and images to tensorboard without tensor ops."""
__author__ = "Michael Gygli"

import tensorflow as tf
from StringIO import StringIO
import matplotlib.pyplot as plt
import numpy as np

class Logger(object):
    """Logging in tensorboard without tensorflow ops."""

kkweon

import tensorflow as tf
import numpy as np
import threading
import gym
import os
from scipy.misc import imresize


def copy_src_to_dst(from_scope, to_scope):
    """Creates a copy variable weights operation

kkweon

#!/usr/bin/env bash

input_video=$1
echo "Input Video: $input_video"

if [ -z "$1" ]; then
        read input_video
fi

echo "Skip Second: "

kkweon

"""
Simple policy gradient in Keras

"""
import gym
import numpy as np

from keras import layers
from keras.models import Model
from keras import backend as K

kkweon

#include <iostream>
using namespace std;

int* testCaseGenerator(int n) {
    int* result = new int[n];

    for(int i = 0; i < n; ++i) {
        result[i] = std::rand() % 99;
    }
    

kkweon