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

hetelek

import tensorflow as tf
import gym

stddev = 1.0
render = True
monitor = True

best_weights = tf.Variable(tf.truncated_normal(shape=[4, 1]))
current_weights = tf.Variable(best_weights.initialized_value())

ffrige

"""
Solves the cartpole-v1 enviroment on OpenAI gym using policy search

Same algorithm as for cartpole-v0

A neural network is used to store the policy

At the end of each episode the target value for each taken action is
updated with the total normalized reward (up to a learning rate)

sparseinference

"""
File: cartpolev1.py
Created: 2017-03-09
By Peter Caven, peter@sparseinference.com
Description:

-- Python 3.6 --

Solve the CartPole-v1 problem:
- this is the same solution as for the 'CartPole-v0' problem, with the episode length extended.

karpathy

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

# hyperparameters
H = 200 # number of hidden layer neurons
batch_size = 10 # every how many episodes to do a param update?
learning_rate = 1e-4
gamma = 0.99 # discount factor for reward

karpathy

"""
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
BSD License
"""
import numpy as np

# data I/O
data = open('input.txt', 'r').read() # should be simple plain text file
chars = list(set(data))
data_size, vocab_size = len(data), len(chars)