def gameover(self, score):
global games_count
global x_train
global y_train
# when game ends, append a data point based on how we lost
if games_count >= 0:
x_train = np.append(x_train, self.last_value)
if self.jumped:
y_train = np.append(y_train, [0])
else:
y_train = np.append(y_train, [1])
# training the model at the end of each run
model.fit(x_train, y_train, epochs=10, verbose=1, shuffle=1)
print(y_train)
games_count += 1
print("x_train:")
print(x_train)
print("y_train ")
print(y_train)
if games_count >= total_number_of_games:
return
controlled_run(self, games_count)
def gameover(self, score):
global games_count
global x_train
global y_train
global model
games_count += 1
# Printing x_train and y_train
print(x_train)
print(y_train)
if games_count is not 0 and games_count % train_frequency is 0:
# Before training, let's make the y_train array categorical
y_train_cat = to_categorical(y_train, num_classes=2)
print(x_train)
# Let's train the network
model.fit(x_train, y_train_cat, epochs=50, verbose=1, shuffle=1)
# Reset x_train and y_train
x_train = np.array([])
y_train = np.array([])
if games_count >= total_number_of_games:
# Let's exit the program now
return
# Let's start another game!
controlled_run(self, games_count)
def gameover(self, score): global games_count games_count += 1 if games_count>=total_number_of_games: # Let's exit the program now return # Let's start another game! controlled_run(self, games_count)
def gameover(self, score):
global games_count
global x_train
global y_train
global model
global all_x
global all_y
global all_scores
global average_scores
global average_score_rate
games_count += 1
# mosntando os valores de x_train e y_train
print(x_train)
print(y_train)
# adicionando os valores de x e y train, em um vetor, para utilizar posteriormente
all_x = np.append(all_x, x_train)
all_y = np.append(all_y, y_train)
all_scores.append(score)
Wrapper.visualize()
#formula para colocar na tabela o media de pontos a nas partidas
if games_count is not 0 and games_count % average_score_rate is 0:
average_score = sum(all_scores) / len(all_scores)
average_scores.append(average_score)
if games_count is not 0 and games_count % train_frequency is 0:
# formula para colocar na tabela da frequencia de treino
y_train_cat = to_categorical(y_train, num_classes=2)
print(x_train)
# Treinar a rede neural
model.fit(x_train, y_train_cat, epochs=50, verbose=1, shuffle=1)
# Resetar o treinamento
x_train = np.array([])
y_train = np.array([])
if games_count >= total_number_of_games:
# Sair do jogo quando atingir o limite de jogos
return
# Começando outro jogo
controlled_run(self, games_count)
def gameover(self, score):
global games_count
global x_train
global y_train
global model
global all_x
global all_y
global all_scores
global average_scores
global average_score_rate
games_count += 1
# Printing x_train and y_train
print(x_train)
print(y_train)
all_x = np.append(all_x, x_train)
all_y = np.append(all_y, y_train)
all_scores.append(score)
Wrapper.visualize()
if games_count is not 0 and games_count % average_score_rate is 0:
average_score = sum(all_scores) / len(all_scores)
average_scores.append(average_score)
if games_count is not 0 and games_count % train_frequency is 0:
# Before training, let's make the y_train array categorical
y_train_cat = to_categorical(y_train, num_classes=2)
print(x_train)
# Let's train the network
model.fit(x_train, y_train_cat, epochs=50, verbose=1, shuffle=1)
# Reset x_train and y_train
x_train = np.array([])
y_train = np.array([])
if games_count >= total_number_of_games:
# Let's exit the program now
return
# Let's start another game!
controlled_run(self, games_count)
def gameover(self, score):
global games_count
global x_train
global y_train
print(x_train)
print(y_train)
if (games_count > 0):
y_train_cat = to_categorical(y_train, num_classes=2)
model.fit(x_train, y_train_cat, epochs=50, verbose=1, shuffle=1)
games_count += 1
if games_count >= total_number_of_games:
return
controlled_run(self, games_count)
def __init__(self): # Start the game controlled_run(self, 0)
def __init__(self):
controlled_run(self, 0)