Jisoo Lee jisoolee0123

## tf_ed_vi_tutorial.py
""" Some description.
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import sys
import json
import tqdm

## 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
	""" Some description.
	"""
	from __future__ import absolute_import
	from __future__ import division
	from __future__ import print_function

	import sys
	import json
	import tqdm
	""" 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