def learn_cartpole(config_path):
env = gym.make('CartPole-v0')
env._max_episode_steps = max_evaluation_steps
# Load configuration.
config = Config(StateMachineGenome, DefaultReproduction,
DefaultSpeciesSet, DefaultStagnation,
config_path)
# Create the population, which is the top-level object for a NEAT run.
p = Population(config)
# Add a stdout reporter to show progress in the terminal.
p.add_reporter(StdOutReporter(True))
stats = StatisticsReporter()
p.add_reporter(stats)
# Run for up for the given number of generations
f = lambda genomes, config: eval_genomes(genomes, config, env=env)
winner = p.run(f, num_generations)
input("Press Enter to continue...")
net = StateMachineNetwork.create(winner, config)
eval_network(net, env, True)
def test_one_state(self):
genome = StateMachineGenome(1)
config = init_config()
genome.configure_new(config)
smn = StateMachineNetwork.create(genome, config)
self.assertEqual(len(smn.states), 1)
self.assertEqual(len(smn.transitions), 1)
def test_create_transition(self):
genome = StateMachineGenome(1)
config = init_config()
genome.configure_new(config)
genome.mutate_add_state(config)
genome.mutate_add_transition(config)
smn = StateMachineNetwork.create(genome, config)
self.assertEqual(len(smn.states), 2)
self.assertEqual(len(smn.transitions), 2)
self.assertEqual(2, len(smn.transitions[1]) + len(smn.transitions[0]))
if __name__ == '__main__':
# First load the genome
genome = pickle.load(open(genome_path, "rb"))
local_dir = os.path.dirname(__file__)
config_path = os.path.join(local_dir, config_name)
config = Config(StateMachineGenome, DefaultReproduction, DefaultSpeciesSet,
DefaultStagnation, config_path)
# Create the environment
env = gym.make(env_name)
# Run the genome
net = StateMachineNetwork.create(genome, config.genome_config)
observation = env.reset()
fitnesses = []
states = [0 for _ in range(len(observation))]
for i in range(num_steps):
output = [
net.activate(states[i], observation[i])
for i in range(len(observation))
]
states = [state for state, _ in output]
actions = [action for _, action in output]
observation, _, _, _ = env.step(actions)
fitnesses.append(env.get_fitness())
# Show plot of fitness over time.
def test_empty_sm_creation(self):
genome = StateMachineGenome(1)
smn = StateMachineNetwork.create(genome, init_config())
self.assertEqual(len(smn.states), 0)
self.assertEqual(len(smn.transitions), 0)
def eval_genomes(genomes, config, env):
for genome_id, genome in genomes:
genome.fitness = 0
net = StateMachineNetwork.create(genome, config)
genome.fitness = eval_network(net, env)
def reset(self, genome, config):
self.net = StateMachineNetwork.create(genome, config.genome_config)
self.current_state = 0