break
# def q_learning():
if __name__ == '__main__':
EPISODES = 50
pin_servo = 9
batch_size = 32
game_name = 'CartPole-v1'
board = Arduino('9600', port='/dev/cu.usbmodem14311')
# demo_(board, pin_servo)
# initialise game
env, state_size, action_size = env_init(game_name)
# initialise agent
agent = DQNAgent(state_size, action_size)
# load model
agent.load("../models/cartpole-dqn.h5")
# train
# agent.train(agent, env, EPISODES, state_size, batch_size)
# save model/agent state
agent.save("cartpole-dqn.h5")
# move servo!!
demo(agent, env, EPISODES, state_size, batch_size)
s.insert(0, [0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
return s
if __name__ == '__main__':
tetris = Tetris()
genetic = None
dict = {}
for e in Figure:
dict[e.name] = e.value
state_size = 200
action_size = 38
agent = DQNAgent(10, action_size)
agent.load("mreza-dqn.h5")
agent.epsilon = 0.12
done = False
episodes = 0
app = TetrisApp()
###############################################################
####################Deo bitan za tetris########################
key_actions = {
'ESCAPE': app.quit,
'LEFT': lambda: app.move(-1),
'RIGHT': lambda: app.move(+1),
'DOWN': lambda: app.drop(True),
'UP': app.rotate_stone,
'p': app.toggle_pause,
'RETURN': app.start_game,
expl_decay=expl_decay,
nhl=nl,
sl_f=sl_f)
batch_size = 16
# Simulation Runtime
testing = 1000
testing_comps = 1
for r in range(4, 5):
# sim_env.T = T_choice[r]
# load Q network
print(r)
parameters = 'old/DQN__S{}_rho{}_SNR{}_PS{}_W4_lr0.0001_df0.0_sl24_nhl1_ef0.9'.format(
r, 0.9, SNR, sim_env.pi)
QN.load(sim_env.channel_type + '/' + parameters)
sim_env = Simulation(number_of_servers=num_of_servers,
number_of_users=1,
historic_time=hist_timeslots,
snr_set=avg_SNR,
csi=0,
channel=0.9)
sim_env.reset()
states = sim_env.state # get first state
for u in range(testing):
states = np.reshape(
states, [1, state_size]) # reshape state to vector for network
action = QN.act_test(states) # get action from DQN agent
# print('SNR:', sim_env.SNR[-1])
# print('action:', sim_env.action[action])
next_state, rewards, overall_err = sim_env.Assign_Cores(
