def startGame(screen):
# set title and icon
pygame.display.set_caption("2048")
icon = pygame.image.load("img/2048_logo.png")
pygame.display.set_icon(icon)
# fill the window screen with brownies background
surf = pygame.Surface((SCREEN_WIDTH, SCREEN_HEIGHT), pygame.SRCALPHA)
surf.fill(color["over"])
screen.blit(surf, (0, 0))
# welcome text to the user
text = 'Welcome to 2048!\n\n' \
'Your goal is to create the number 2048 by sliding the numbers on the grid\n' \
'command are:\n'\
'W to Move Up\n' \
'S to Move Down\n'\
'A to Move Left\n' \
'D to Move Right\n' \
'if you want to quit press Q\n\n'\
'Good Luck! :) \n'
# print on screen
blit_text(screen, text, (70, 20), myfont)
pygame.display.update()
sleep(3)
# initialize the game and run it
board = Game(screen)
board.playGame()
def play_game(neuralNetwork, visual=False):
game2048 = Game()
moves = [['a', 's'], ['d', 'w']]
while (not game2048.is_stale()):
if game2048.stale_count == 0:
state = game2048.get_state()
inputs = []
for num in state:
val = 0 if num == 0 else math.log(num, 2)
inputs += trans(int(val))
outputs = neuralNetwork.eval(inputs)
game2048.process_move(moves[outputs[0]][outputs[1]], visual)
else:
game2048.process_move(
moves[random.randint(0, 1)][random.randint(0, 1)], visual)
return game2048.score
def play_game (neuralNetwork, visual=False): game2048 = Game () moves = [['a', 's'], ['d', 'w']] while (not game2048.is_stale ()): if game2048.stale_count == 0: state = game2048.get_state () inputs = [] for num in state: val = 0 if num == 0 else math.log (num, 2) inputs += trans (int (val)) outputs = neuralNetwork.eval (inputs) game2048.process_move (moves [outputs [0]] [outputs [1]], visual) else: game2048.process_move (moves [random.randint (0, 1)] [random.randint (0, 1)], visual) return game2048.score
def eval (self): _map = ['w', 's', 'a', 'd'] scores = [] for a in range (10): g = Game () while (not g.is_stale ()): state_ = g.get_state () state = [0 for a in range (16)] for i in range (len (state_)): if state_ [i] != 0: state [i] = math.log (state_ [i], 2) / 8.0 in_ = np.array (state) out = self.graph.evaluate (in_) [0] g.process_move (_map [out]) scores += [g.get_score ()] return (sum (scores) / 10.0) ** 2
class qNet2048(object):
EPOCH = 2000
def __init__(self):
self.net = Net(20, 50, 1)
self.net.setEpoch(1)
self.gamma = 0.8
self.main()
def main(self):
self.train()
self.playGame()
def playGame(self):
self.initNewGame()
i = 0
while self.gameRuning:
print(' Move:', i)
i += 1
self.game.Print()
(action, bestValue) = self.getMaxQ()
self.game.Move(action)
i += 1
print(' Epoch:', i)
self.game.Print()
def train(self):
for i in range(self.EPOCH):
print('Game Epoch:', i + 1, '/', self.EPOCH, end='\r')
self.initNewGame()
while self.gameRuning:
state = self.gridToVector()
action = random.choice(list(DIRECTION))
self.game.Move(action)
(action, bestValue) = self.getMaxQ()
inValue = state + self.directionToVector(action)
newQ = self.game.GetLastMoveScore() + self.gamma * bestValue
self.net.Train([inValue], [[newQ]])
print('\nScore: ', self.game.GetTotalScore())
print()
def getMaxQ(self):
directions = self.simDirections()
best = max(directions, key=directions.get)
return (best, directions[best][0])
def simDirections(self):
gridVector = self.gridToVector()
result = {}
for direction in DIRECTION:
inputArray = gridVector[:] + self.directionToVector(direction)
result[direction] = self.net.Sim(inputArray)
return result
def directionToVector(self, direction):
if direction == DIRECTION.LEFT:
return [1.0, 0.0, 0.0, 0.0]
if direction == DIRECTION.RIGHT:
return [0.0, 1.0, 0.0, 0.0]
if direction == DIRECTION.UP:
return [0.0, 0.0, 1.0, 0.0]
if direction == DIRECTION.DOWN:
return [0.0, 0.0, 0.0, 1.0]
def gridToVector(self):
tab = self.game.GetGrid()
i = []
for row in tab:
i += row
maxValue = max(i)
return [x / maxValue for x in i]
def initNewGame(self):
self.game = Game()
self.game.onGameOver(self.handleGameOver)
self.gameRuning = True
def handleGameOver(self):
self.gameRuning = False
def initNewGame(self):
self.game = Game()
self.game.onGameOver(self.handleGameOver)
self.gameRuning = True
# if not found, create a new one if not spec: spec = Species (state) r = RewardInfo () self.species [s] = r return spec, r # return reward for inputted state return spec, self.species [spec] g = Game () sm = StateManager () scores = [] random_moves = [] informed_moves = [] dif_states = [] x_data = [] running_length = 500 averages = [] num_games = int (4 * 1e3) print 'Playing %s games.' % num_games
