from examples.experiment_functions import SMSwarmExperimentRunner
from examples.experiment_template import SingleExperiment
# Important variables.
from neat.state_machine_genome import StateMachineGenome
experiment_name = 'SM_4_reference_block_long'
num_steps = 3000
num_generations = 200
num_runs = 1
config_name = 'config-state_machine'
if __name__ == '__main__':
env = gym.make('tiling-pattern11x11-block-v0')
runner = SMSwarmExperimentRunner(env, num_steps)
# Create learning configuration.
local_dir = os.path.dirname(__file__)
config_path = os.path.join(local_dir, config_name)
config = neat.Config(StateMachineGenome, neat.DefaultReproduction,
neat.DefaultSpeciesSet, neat.DefaultStagnation,
config_path)
# Create and run experiment.
experiment = SingleExperiment(config, runner, num_generations,
experiment_name)
for i in range(num_runs):
experiment.run(experiment_name + str(i))
from examples.experiment_functions import NEATSwarmExperimentRunner
from examples.experiment_template import SingleExperiment
# This script describes an state machine experiment where all the values are specified in a config file.
# Config file can and should be given as a parameter.
from neat import Config, DefaultReproduction, DefaultSpeciesSet, DefaultStagnation, DefaultGenome
from neat.state_machine_genome import StateMachineGenome
if __name__ == '__main__':
if len(sys.argv) != 2:
print('One argument expected, which is the path to the config file.')
else:
config_name = sys.argv[1]
# Create learning configuration.
local_dir = os.path.dirname(__file__)
config_path = os.path.join(local_dir, config_name)
config = Config(DefaultGenome, DefaultReproduction, DefaultSpeciesSet,
DefaultStagnation, config_path)
env = gym.make(config.env_name)
runner = NEATSwarmExperimentRunner(env, config.num_steps)
# Create and run experiment.
experiment = SingleExperiment(config, runner, config.num_generations,
config.experiment_name)
for i in range(config.num_runs):
experiment.run(config.experiment_name + str(i))
import gym
from examples.experiment_functions import NEATSwarmExperimentRunner
from examples.experiment_template import SingleExperiment
# Important variables.
experiment_name = 'NEAT_foraging_11x11_static'
num_steps = 3000
num_robots = 5
num_generations = 100
num_runs = 5
config_name = 'config-feedforward-11x11'
if __name__ == '__main__':
env = gym.make('foraging11x11-static-v0')
runner = NEATSwarmExperimentRunner(env, num_steps)
# Create learning configuration.
local_dir = os.path.dirname(__file__)
config_path = os.path.join(local_dir, config_name)
config = neat.Config(neat.DefaultGenome, neat.DefaultReproduction,
neat.DefaultSpeciesSet, neat.DefaultStagnation,
config_path)
# Create and run experiment.
experiment = SingleExperiment(config, runner, num_generations,
experiment_name)
experiment.run(experiment_name)
num_robots = 5
num_generations = 100
num_runs = 1
config_name = 'config-feedforward-50x50'
gym.register(id='foraging50x50-distance-sum-v0',
entry_point='gym_multi_robot.envs:ForagingEnv',
kwargs={
'env_storage_path': 'foraging50x50.pickle',
'game_cls': ClosestGame
})
if __name__ == '__main__':
env = gym.make('foraging50x50-distance-sum-v0')
runner = NEATSwarmExperimentRunner(env, num_steps)
# Create learning configuration.
local_dir = os.path.dirname(__file__)
config_path = os.path.join(local_dir, config_name)
config = neat.Config(neat.DefaultGenome, neat.DefaultReproduction,
neat.DefaultSpeciesSet, neat.DefaultStagnation,
config_path)
# Create and run experiment.
experiment = SingleExperiment(config, runner, num_generations,
experiment_name, 2)
for i in range(num_runs):
experiment.run(experiment_name + str(num_runs))