def simple_test(env_fn, learn_fn, min_reward_fraction, n_trials=N_TRIALS):
np.random.seed(0)
np_random.seed(0)
env = DummyVecEnv([env_fn])
with tf.Graph().as_default(), tf.Session(config=tf.ConfigProto(allow_soft_placement=True)).as_default():
tf.set_random_seed(0)
model = learn_fn(env)
sum_rew = 0
done = True
for i in range(n_trials):
if done:
obs = env.reset()
state = model.initial_state
if state is not None:
a, v, state, _ = model.step(obs, S=state, M=[False])
else:
a, v, _, _ = model.step(obs)
obs, rew, done, _ = env.step(a)
sum_rew += float(rew)
print("Reward in {} trials is {}".format(n_trials, sum_rew))
assert sum_rew > min_reward_fraction * n_trials, \
'sum of rewards {} is less than {} of the total number of trials {}'.format(sum_rew, min_reward_fraction, n_trials)
def test_serialization(learn_fn, network_fn):
'''
Test if the trained model can be serialized
'''
if network_fn.endswith('lstm') and learn_fn in [
'acktr', 'trpo_mpi', 'deepq'
]:
# TODO make acktr work with recurrent policies
# and test
# github issue: https://github.com/openai/baselines/issues/660
return
env = DummyVecEnv([lambda: MnistEnv(10, episode_len=100)])
ob = env.reset().copy()
learn = get_learn_function(learn_fn)
kwargs = {}
kwargs.update(network_kwargs[network_fn])
kwargs.update(learn_kwargs[learn_fn])
learn = partial(learn, env=env, network=network_fn, seed=0, **kwargs)
with tempfile.TemporaryDirectory() as td:
model_path = os.path.join(td, 'serialization_test_model')
with tf.Graph().as_default(), make_session().as_default():
model = learn(total_timesteps=100)
model.save(model_path)
mean1, std1 = _get_action_stats(model, ob)
variables_dict1 = _serialize_variables()
with tf.Graph().as_default(), make_session().as_default():
model = learn(total_timesteps=0, load_path=model_path)
mean2, std2 = _get_action_stats(model, ob)
variables_dict2 = _serialize_variables()
for k, v in variables_dict1.items():
np.testing.assert_allclose(
v,
variables_dict2[k],
atol=0.01,
err_msg='saved and loaded variable {} value mismatch'.format(
k))
np.testing.assert_allclose(mean1, mean2, atol=0.5)
np.testing.assert_allclose(std1, std2, atol=0.5)
def test_function():
with tf.Graph().as_default():
x = tf.placeholder(tf.int32, (), name="x")
y = tf.placeholder(tf.int32, (), name="y")
z = 3 * x + 2 * y
lin = function([x, y], z, givens={y: 0})
with single_threaded_session():
initialize()
assert lin(2) == 6
assert lin(2, 2) == 10
def test_multikwargs():
with tf.Graph().as_default():
x = tf.placeholder(tf.int32, (), name="x")
with tf.variable_scope("other"):
x2 = tf.placeholder(tf.int32, (), name="x")
z = 3 * x + 2 * x2
lin = function([x, x2], z, givens={x2: 0})
with single_threaded_session():
initialize()
assert lin(2) == 6
assert lin(2, 2) == 10
def test_coexistence(learn_fn, network_fn):
'''
Test if more than one model can exist at a time
'''
if learn_fn == 'deepq':
# TODO enable multiple DQN models to be useable at the same time
# github issue https://github.com/openai/baselines/issues/656
return
if network_fn.endswith('lstm') and learn_fn in [
'acktr', 'trpo_mpi', 'deepq'
]:
# TODO make acktr work with recurrent policies
# and test
# github issue: https://github.com/openai/baselines/issues/660
return
env = DummyVecEnv([lambda: gym.make('CartPole-v0')])
learn = get_learn_function(learn_fn)
kwargs = {}
kwargs.update(network_kwargs[network_fn])
kwargs.update(learn_kwargs[learn_fn])
learn = partial(learn,
env=env,
network=network_fn,
total_timesteps=0,
**kwargs)
make_session(make_default=True, graph=tf.Graph())
model1 = learn(seed=1)
make_session(make_default=True, graph=tf.Graph())
model2 = learn(seed=2)
model1.step(env.observation_space.sample())
model2.step(env.observation_space.sample())
def reward_per_episode_test(env_fn, learn_fn, min_avg_reward, n_trials=N_EPISODES):
env = DummyVecEnv([env_fn])
with tf.Graph().as_default(), tf.Session(config=tf.ConfigProto(allow_soft_placement=True)).as_default():
model = learn_fn(env)
N_TRIALS = 100
observations, actions, rewards = rollout(env, model, N_TRIALS)
rewards = [sum(r) for r in rewards]
avg_rew = sum(rewards) / N_TRIALS
print("Average reward in {} episodes is {}".format(n_trials, avg_rew))
assert avg_rew > min_avg_reward, \
'average reward in {} episodes ({}) is less than {}'.format(n_trials, avg_rew, min_avg_reward)
def test_env_after_learn(algo):
def make_env():
# acktr requires too much RAM, fails on travis
env = gym.make('CartPole-v1' if algo ==
'acktr' else 'PongNoFrameskip-v4')
return env
make_session(make_default=True, graph=tf.Graph())
env = SubprocVecEnv([make_env])
learn = get_learn_function(algo)
# Commenting out the following line resolves the issue, though crash happens at env.reset().
learn(network='mlp', env=env, total_timesteps=0, load_path=None, seed=None)
env.reset()
env.close()