return True
if not os.path.isfile("./" + RUN_DIR + "/pickledPops/Gen_0.pickle"):
random.seed(SEED)
np.random.seed(SEED)
my_sim = Sim(dt_frac=DT_FRAC, simulation_time=SIM_TIME, fitness_eval_init_time=INIT_TIME)
my_env = Env(temp_amp=TEMP_AMP, fluid_environment=FLUID_ENV, aggregate_drag_coefficient=AGGREGATE_DRAG_COEF,
lattice_dimension=VOXEL_SIZE, grav_acc=GRAV_ACC, frequency=FREQ, muscle_stiffness=STIFFNESS,
block_position=BLOCK_POS, block_material=BLOCK_MAT, external_block=True)
my_objective_dict = ObjectiveDict()
my_objective_dict.add_objective(name="fitness", maximize=True, tag=FITNESS_TAG,
# meta_func=min_energy
)
my_objective_dict.add_objective(name="age", maximize=False, tag=None)
my_objective_dict.add_objective(name="n_muscle", maximize=False, tag=None,
node_func=partial(count_occurrences, keys=[3]),
output_node_name="material")
# logging only:
my_objective_dict.add_objective(name="n_vox", maximize=False, tag=None, logging_only=True,
node_func=partial(count_occurrences, keys=[1, 3]),
output_node_name="material")
my_pop = Population(my_objective_dict, MyGenotype, MyPhenotype, pop_size=POP_SIZE)
# print np.sum(np.random.rand(*IND_SIZE)) # seed=1; 226.98967645847415
MyGenotype.NET_DICT = {"phase_offset": np.random.rand(*IND_SIZE)}
my_sim = Sim(dt_frac=DT_FRAC,
simulation_time=SIM_TIME,
fitness_eval_init_time=INIT_TIME)
my_env = Env(temp_amp=TEMP_AMP,
fluid_environment=FLUID_ENV,
aggregate_drag_coefficient=AGGREGATE_DRAG_COEF,
lattice_dimension=VOXEL_SIZE,
grav_acc=GRAV_ACC,
frequency=FREQ,
muscle_stiffness=STIFFNESS)
my_objective_dict = ObjectiveDict()
my_objective_dict.add_objective(name="fitness",
maximize=True,
tag="<normAbsoluteDisplacement>")
my_objective_dict.add_objective(name="age", maximize=False, tag=None)
my_pop = Population(my_objective_dict,
MyGenotype,
Phenotype,
pop_size=POP_SIZE)
my_optimization = ParetoOptimization(my_sim, my_env, my_pop)
my_optimization.run(max_hours_runtime=MAX_TIME,
max_gens=MAX_GENS,
num_random_individuals=NUM_RANDOM_INDS,
directory=RUN_DIR,
random.seed(SEED)
np.random.seed(SEED)
my_sim = Sim(dt_frac=DT_FRAC,
simulation_time=SIM_TIME,
fitness_eval_init_time=INIT_TIME)
my_env = Env(temp_amp=TEMP_AMP,
fluid_environment=FLUID_ENV,
aggregate_drag_coefficient=AGGREGATE_DRAG_COEF,
lattice_dimension=VOXEL_SIZE,
grav_acc=GRAV_ACC,
frequency=FREQ,
muscle_stiffness=STIFFNESS)
my_objective_dict = ObjectiveDict()
my_objective_dict.add_objective(name="fitness",
maximize=True,
tag=FITNESS_TAG,
meta_func=favor_appendages)
my_objective_dict.add_objective(name="age", maximize=False, tag=None)
my_pop = Population(my_objective_dict,
MyGenotype,
MyPhenotype,
pop_size=POP_SIZE)
my_optimization = ParetoOptimization(my_sim, my_env, my_pop)
my_optimization.run(max_hours_runtime=MAX_TIME,
max_gens=MAX_GENS,
num_random_individuals=NUM_RANDOM_INDS,
my_sim = Sim(dt_frac=DT_FRAC,
simulation_time=SIM_TIME,
fitness_eval_init_time=INIT_TIME)
my_env = Env(
temp_amp=TEMP_AMP,
frequency=FREQ,
muscle_stiffness=STIFFNESS,
fat_stiffness=STIFFNESS,
# fluid_environment=FLUID_ENV, aggregate_drag_coefficient=AGGREGATE_DRAG_COEF,
lattice_dimension=VOXEL_SIZE,
grav_acc=GRAV_ACC,
)
my_objective_dict = ObjectiveDict()
my_objective_dict.add_objective(name="fitness",
maximize=True,
tag="<normAbsoluteDisplacement>")
my_objective_dict.add_objective(name="age", maximize=False, tag=None)
# logging only:
my_objective_dict.add_objective(name="n_muscle",
maximize=False,
tag=None,
logging_only=True,
node_func=partial(count_occurrences,
keys=[3]),
output_node_name="material")
# logging only:
my_objective_dict.add_objective(name="n_vox",