Q_train = deepQNetwork.DeepQNetwork(height, width, historyLength,
n_actions, gamma, learningRate,
SEED)
with tf.variable_scope("target") as target_scope:
Q_target = deepQNetwork.DeepQNetwork(height, width, historyLength,
n_actions, gamma, learningRate,
SEED)
sess = tf.InteractiveSession()
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver(max_to_keep=None)
if loadModel is True:
saver.restore(sess, modelPath)
log = myLog.Log(logPath, 'w+')
print time.strftime(MYTIMEFORMAT, time.localtime())
print 'simulation start!'
memory = Memory.Memory(path=dataPath,
size=memorySize,
historySize=historyLength,
dims=[height, width],
seed=SEED)
State0 = np.zeros([batchSize, network_size])
State1 = np.zeros([batchSize, network_size])
Action0 = np.zeros([batchSize])
Reward0 = np.zeros([batchSize])
Terminal = np.zeros([batchSize])
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.allow_soft_placement = True
sess = tf.InteractiveSession(config=config)
sess.run(tf.initialize_all_variables())
frameStart = 0
saver = tf.train.Saver(max_to_keep=None)
if loadModel is True:
print 'Loading model from %s ...' % pathModel,
saver.restore(sess, pathModel)
print 'Finished\n'
# frameStart = freqTest
log = myLog.Log(pathLog, 'w+')
print time.strftime(MYTIMEFORMAT, time.localtime()), '\n'
print open('Options.py').read()
print 'SEED = %d\n' % SEED
memory = Memory.Memory(opt)
if loadData is True:
print 'Loading data from %s ...' % pathData,
memory.load(pathData)
print 'Finished\n'
trainStart = False
cost_average = 0.0
Q_average = 0.0
