def evaluate_population(population):
twelve_degrees = 0.2094384 #radians
num_steps = 10**5
for chromo in population:
net = nn.create_phenotype(chromo)
# initial conditions (as used by Stanley)
x = random.randint(0, 4799)/1000.0 - 2.4
x_dot = random.randint(0, 1999)/1000.0 - 1.0
theta = random.randint(0, 399)/1000.0 - 0.2
theta_dot = random.randint(0, 2999)/1000.0 - 1.5
#x = 0.0
#x_dot = 0.0
#theta = 0.0
#theta_dot = 0.0
fitness = 0
for trials in xrange(num_steps):
# maps into [0,1]
inputs = [(x + 2.4)/4.8,
(x_dot + 0.75)/1.5,
(theta + twelve_degrees)/0.41,
(theta_dot + 1.0)/2.0]
# a normalizacao so acontece para estas condicoes iniciais
# nada garante que a evolucao do sistema leve a outros
# valores de x, x_dot e etc...
action = net.pactivate(inputs)
# Apply action to the simulated cart-pole
x, x_dot, theta, theta_dot = cart_pole(action[0], x, x_dot, theta, theta_dot)
# Check for failure. If so, return steps
# the number of steps indicates the fitness: higher = better
fitness += 1
if (abs(x) >= 2.4 or abs(theta) >= twelve_degrees):
#if abs(theta) > twelve_degrees: # Igel (p. 5) uses theta criteria only
# the cart/pole has run/inclined out of the limits
break
chromo.fitness = fitness
from random import randint
import cPickle as pickle
import single_pole
chromosome.node_gene_type = genome2.NodeGene
# load the winner
file = open('winner_chromosome', 'r')
c = pickle.load(file)
file.close()
print 'Loaded chromosome:'
print c
config.load('spole_config')
net = nn.create_phenotype(c)
#x = 0.0
#x_dot = 0.0
#theta = 0.0
#theta_dot = 0.0
# initial conditions (as used by Stanley)
x = randint(0, 4799)/1000.0 - 2.4
x_dot = randint(0, 1999)/1000.0 - 1.0
theta = randint(0, 399)/1000.0 - 0.2
theta_dot = randint(0, 2999)/1000.0 - 1.5
print "\nInitial conditions:"
print "%2.4f %2.4f %2.4f %2.4f" %(x, x_dot, theta, theta_dot)
from random import randint
import cPickle as pickle
import single_pole
chromosome.node_gene_type = genome2.NodeGene
# load the winner
file = open('winner_chromosome', 'r')
c = pickle.load(file)
file.close()
print 'Loaded chromosome:'
print c
config.load('spole_config')
net = nn.create_phenotype(c)
#x = 0.0
#x_dot = 0.0
#theta = 0.0
#theta_dot = 0.0
# initial conditions (as used by Stanley)
x = randint(0, 4799) / 1000.0 - 2.4
x_dot = randint(0, 1999) / 1000.0 - 1.0
theta = randint(0, 399) / 1000.0 - 0.2
theta_dot = randint(0, 2999) / 1000.0 - 1.5
print "\nInitial conditions:"
print "%2.4f %2.4f %2.4f %2.4f" % (x, x_dot, theta, theta_dot)
for step in xrange(10**5):
