flyman3046

# https://gist.github.com/karpathy/77fbb6a8dac5395f1b73e7a89300318d
import gym
import numpy as np

def f(env, weight):
    total_reward = 0.0
    num_run = 100
    for t in range(num_run):
        observation = env.reset()
        for i in range(300):

flyman3046

# Simulated data and plot comes from: http://cs231n.github.io/neural-networks-case-study/
import tensorflow as tf
import numpy as np
import random
import matplotlib.pyplot as plt

plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'

flyman3046

# Solve CartPole-v0

import tensorflow as tf
import numpy as np
import gym
import matplotlib.pyplot as plt

# hyperparameters
H = 10 # number of hidden layer neurons
learning_rate = 1e-3

flyman3046

# original code: https://github.com/kvfrans/openai-cartpole/blob/master/cartpole-policygradient.py

import tensorflow as tf
import numpy as np
import random
import gym
import math
import matplotlib.pyplot as plt

def softmax(x):

flyman3046

# Original code from https://gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5
# Use it to solve MountainCar-v0

import numpy as np
import gym
import matplotlib.pyplot as plt

# hyperparameters
H = 10 # number of hidden layer neurons
batch_size = 1 # every how many episodes to do a param update?

flyman3046

# Original code from https://gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5
# Use it to solve CartPole-v0
import numpy as np
import gym

# hyperparameters
H = 10 # number of hidden layer neurons
batch_size = 5 # every how many episodes to do a param update?
learning_rate = 1e-3
gamma = 0.99 # discount factor for reward

flyman3046

# Original code from https://gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5
# Use it to solve CartPole-v0
import numpy as np
import gym

# hyperparameters
H = 10 # number of hidden layer neurons
batch_size = 5 # every how many episodes to do a param update?
learning_rate = 1e-2
gamma = 0.99 # discount factor for reward