def __init__(self,
epsilon=0,
gamma=0.97,
memory_capacity=10000,
batch_size=4,
learning_rate=0.001,
Q_1=None,
num_inputs=None,
num_actions=None,
params_path=None,
memory_path=None):
self.state = None
self.is_terminal = False
self.action = None
self.reward = 0
self.episode = 0
# DQL
self.epsilon = epsilon # Exploitation or exploration
self.gamma = gamma # Discount factor
self.memory_capacity = memory_capacity
self.batch_size = batch_size
self.learning_rate = learning_rate
self.num_inputs = num_inputs
self.num_actions = num_actions
# Replay memory
self.exp_bank = self.reset_memory()
if memory_path and os.path.exists(memory_path):
memory = np.load(memory_path, allow_pickle=True)
self.exp_bank.memory = memory['exp_bank'].tolist()
print("loaded memory_bank")
# Action-value function
if Q_1 is not None:
self.Q_1 = Q_1
self.num_inputs = self.Q_1.layers[0].input_shape
self.num_actions = self.Q_1.layers[-1].output_shape
elif num_actions is not None:
self.Q_1 = models.Sequential()
self.Q_1.add(
layers.Dense(self.num_inputs, activation=activations.relu))
self.Q_1.add(layers.Dense(10, activation=activations.sigmoid))
self.Q_1.add(layers.Dense(20, activation=activations.sigmoid))
self.Q_1.add(
layers.Dense(self.num_actions, activation=activations.softmax))
self.Q_1.compile()
else:
raise ValueError()
if params_path:
self.Q_1.load_params(params_path)
self.Q_2 = self.Q_1
self.Q_2 = self.Q_1
fig.suptitle('Algorithm accuracy for each epoch', fontsize=16)
# for i in range(len(acc)):
# ax.annotate('{} = {}'.format(i + 1, np.round(acc[i] * 100, 1)), (i, acc[i] * 100 + 0.4), ha='center', va='center')
k = acc.shape[0] - 1
ax.annotate('Epoch {} = {}%'.format(k + 1, np.round(acc[k] * 100, 1)),
(k, acc[k] * 100),
ha='center',
va='center')
plt.draw()
plt.pause(.001)
print('Loading data...')
dataset = load_mnist_data(file_path="400_imgs.npz")
M = models.Sequential()
M.add(layers.Reshape((1, 28, 28), input_shape=(1, 784)))
M.add(
layers.Conv2D(15,
kernel_size=(3, 3),
input_shape=(1, 28, 28),
padding="same",
activation=activations.leaky_relu))
M.add(layers.MaxPooling2D((2, 2)))
M.add(layers.Flatten())
M.add(layers.Dense(100, activation=activations.leaky_relu))
M.add(layers.Dense(10, activation=activations.softmax))
M.compile()
M.description()