Keith Gould keithmgould

## cartpole_pg.py
#!/usr/bin/env python

import gym
import numpy as np
import tensorflow as tf

from tensorflow.python.ops import random_ops

def _initializer(shape, dtype=tf.float32, partition_info=None):
     return random_ops.random_normal(shape)

## pg-pong.py
""" 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

## undeployed.sh
alias undeployed="heroku releases -a APP_NAME | sed -n 2p | cut -d' ' -f4 | xargs -J % git log --oneline --decorate --color --graph master --not %"
	#!/usr/bin/env python

	import gym
	import numpy as np
	import tensorflow as tf

	from tensorflow.python.ops import random_ops

	def _initializer(shape, dtype=tf.float32, partition_info=None):
	return random_ops.random_normal(shape)
	""" 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