def test_current_context(self):
"""Check the functionality of the current_context attribute.
This method is tested for the following cases:
1. no context
2. random contexts
3. fixed single context
4. fixed multiple contexts
"""
np.random.seed(0)
random.seed(0)
# test case 1
env = AntMaze(use_contexts=False)
env.reset()
self.assertIsNone(env.current_context)
# test case 2
env = AntMaze(use_contexts=True, random_contexts=True,
context_range=[(-4, 5), (4, 20)])
env.reset()
np.testing.assert_almost_equal(
env.current_context, np.array([3.5997967, 16.1272704]))
# test case 3
env = AntMaze(use_contexts=True, random_contexts=False,
context_range=[-4, 5])
env.reset()
np.testing.assert_almost_equal(
env.current_context, np.array([-4, 5]))
# test case 4
env = AntMaze(use_contexts=True, random_contexts=False,
context_range=[[-4, 5], [-3, 6], [-2, 7]])
env.reset()
np.testing.assert_almost_equal(
env.current_context, np.array([-3, 6]))
env.reset()
np.testing.assert_almost_equal(
env.current_context, np.array([-4, 5]))
def _create_env(env, evaluate=False):
"""Return, and potentially create, the environment.
Parameters
----------
env : str or gym.Env
the environment, or the name of a registered environment.
evaluate : bool, optional
specifies whether this is a training or evaluation environment
Returns
-------
gym.Env
a gym-compatible environment
"""
if env == "AntMaze":
if evaluate:
env = AntMaze(use_contexts=True, context_range=[16, 0])
# env = AntMaze(use_contexts=True, context_range=[16, 16])
# env = AntMaze(use_contexts=True, context_range=[0, 16])
else:
env = AntMaze(use_contexts=True,
random_contexts=True,
context_range=[(-4, 20), (-4, 20)])
elif env == "AntPush":
if evaluate:
env = AntPush(use_contexts=True, context_range=[0, 19])
else:
env = AntPush(use_contexts=True, context_range=[0, 19])
# env = AntPush(use_contexts=True,
# random_contexts=True,
# context_range=[(-16, 16), (-4, 20)])
elif env == "AntFall":
if evaluate:
env = AntFall(use_contexts=True, context_range=[0, 27, 4.5])
else:
env = AntFall(use_contexts=True, context_range=[0, 27, 4.5])
# env = AntFall(use_contexts=True,
# random_contexts=True,
# context_range=[(-4, 12), (-4, 28), (0, 5)])
elif env in [
"figureeight0", "figureeight1", "figureeight2", "merge0",
"merge1", "merge2", "bottleneck0", "bottleneck1",
"bottleneck2", "grid0", "grid1"
]:
# Import the benchmark and fetch its flow_params
benchmark = __import__("flow.benchmarks.{}".format(env),
fromlist=["flow_params"])
flow_params = benchmark.flow_params
# Get the env name and a creator for the environment.
create_env, env_name = make_create_env(flow_params, version=0)
# Create the environment.
env = create_env()
elif isinstance(env, str):
# This is assuming the environment is registered with OpenAI gym.
env = gym.make(env)
# Reset the environment.
if env is not None:
env.reset()
return env