import pytest
from metaworld.benchmarks import ML1, MT10, ML10, ML45, MT50
from tests.helpers import step_env
@pytest.mark.parametrize('name', ML1.available_tasks())
def test_all_ml1(name):
train_env = ML1.get_train_tasks(name)
tasks = train_env.sample_tasks(11)
for t in tasks:
train_env.set_task(t)
step_env(train_env, max_path_length=3)
train_env.close()
del train_env
test_env = ML1.get_test_tasks(name)
tasks = test_env.sample_tasks(11)
for t in tasks:
test_env.set_task(t)
step_env(test_env, max_path_length=3)
test_env.close()
del test_env
def test_all_ml10():
ml10_train_env = ML10.get_train_tasks()
train_tasks = ml10_train_env.sample_tasks(11)
for t in train_tasks:
from metaworld.benchmarks import ML1
import time
print(ML1.available_tasks()) # Check out the available tasks
env = ML1.get_train_tasks(
'pick-place-v1') # Create an environment with task `pick_place`
tasks = env.sample_tasks(1) # Sample a task (in this case, a goal variation)
env.set_task(tasks[0]) # Set task
obs = env.reset() # Reset environment
for i in range(1000):
print('iteration %d' % (i))
if i % 100 == 0:
obs = env.reset()
env.render()
a = env.action_space.sample() # Sample an action
obs, reward, done, info = env.step(a)
print(obs) # Step the environoment with the sampled random action
time.sleep(0.2)
