) # use "fancy" for full background, random bird color and random pipe color, use "fixed" (default) for black background and constant bird and pipe colors.
p = PLE(game,
fps=30,
frame_skip=1,
num_steps=1,
force_fps=True,
display_screen=True)
# Note: if you want to see you agent act in real time, set force_fps to False. But don't use this setting for learning, just for display purposes.
p.init()
reward = 0.0
nb_games = 10
cumulated = np.zeros((nb_games))
for i in range(nb_games):
p.reset_game()
while (not p.game_over()):
state = game.getGameState()
action = FlappyPolicy(state,
None) ### Your job is to define this function.
reward = p.act(action)
cumulated[i] = cumulated[i] + reward
average_score = np.mean(cumulated)
max_score = np.max(cumulated)
print(f"average_score: {average_score}")
print(f"max_score: {max_score}")
fps=30,
frame_skip=1,
num_steps=1,
force_fps=True,
display_screen=True)
# Note: if you want to see you agent act in real time, set force_fps to False. But don't use this setting for learning, just for display purposes.
p.init()
reward = 0.0
nb_games = 10
cumulated = np.zeros((nb_games))
for i in range(nb_games):
p.reset_game()
while (not p.game_over()):
state = game.getGameState()
screen = p.getScreenRGB()
action = FlappyPolicy(state,
screen) ### Your job is to define this function.
reward = p.act(action)
cumulated[i] = cumulated[i] + reward
average_score = np.mean(cumulated)
max_score = np.max(cumulated)
print(average_score)
print(max_score)
p = PLE(game,
fps=30,
frame_skip=1,
num_steps=1,
force_fps=False,
display_screen=True)
# Note: if you want to see you agent act in real time, set force_fps to False. But don't use this setting for learning, just for display purposes.
p.init()
reward = 0.0
nb_games = 20
cumulated = np.zeros((nb_games))
for i in range(nb_games):
p.reset_game()
while (not p.game_over()):
state = game.getGameState()
screen = p.getScreenRGB()
action = FlappyPolicy(state, screen)
reward = p.act(action)
cumulated[i] = cumulated[i] + reward
print("Game {} over, score : {}".format(i + 1, cumulated[i]))
average_score = np.mean(cumulated)
max_score = np.max(cumulated)
print("average_score : {}".format(average_score))
print("max_score {}".format(max_score))