def test_evolution(self):
p = Population(10, 3, 1)
status = p.get_status()
for s in status.keys():
output = []
for i in range(status.get(s, 0)):
output.append(p.run(s, i, [1, 2, 3]))
p.set_score(s, i, 1)
p.evolve()
def test_flow(self):
p = Population(10, 3, 1)
for _ in range(100):
status = p.get_status()
for s in status.keys():
output = []
for i in range(status.get(s, 0)):
out = p.run(s, i, [1, 2, 3])[0]
output.append(out)
p.set_score(s, i, random.randrange(1, 10))
print(s, output)
p.evolve()
# print a sample
pr = Printer(p.population[next(iter(p.population))][0])
pr.print()
def train():
env = gym.make('LunarLanderContinuous-v2')
try:
p = Population.load(FULLNAME)
print('Existing state loaded')
except FileNotFoundError as e:
print(str(e) + '. Creating new state')
p = Population(10000, env.observation_space.shape[0],
env.action_space.shape[0])
while True:
try:
max_reward = -99999
status = p.get_status()
for s in status.keys():
for i in range(status.get(s, 0)):
ob = env.reset()
reward_sum = 0
while True:
action = action_final_activation(p.run(s, i, ob))
ob, reward, done, info = env.step(action)
reward_sum = reward_sum + reward
if done:
break
p.set_score(s, i, reward_sum)
max_reward = np.max([reward_sum, max_reward])
print(p.generation, max_reward, p.population.keys())
try:
p.save(AUTOSAVE)
except RuntimeError as e:
print('error saving: {}'.format(str(e)))
p.evolve()
except KeyboardInterrupt as e:
try:
print('\nsaving before exit')
p.save(FULLNAME)
sys.exit('Bye!')
except RuntimeError as e:
print('error saving: {}'.format(str(e)))
min_position = np.min([min_position, ob[0]])
reward_sum = reward_sum + reward
if done:
break
reward_sum = reward_sum + ((max_position + 1.2) - (min_position + 1.2))
max_reward = np.max([reward_sum, max_reward])
p.set_score(s, i, reward_sum)
if max_position >= target_reward:
winner = (s, i)
break
if max_position >= target_reward:
break
print('Generation: {} Score: {} Max position: {} Population: {}'.format(p.generation, reward_sum, max_position, p.population.keys()))
if max_position >= target_reward:
break
p.evolve()
print('Species {} is the winner'.format(winner[0]))
ob = env.reset()
while True:
action = action = p.run(winner[0], winner[1], ob)
ob, reward, done, info = env.step(np.argmax(action))
env.render()
if done:
ob = env.reset()