gaspersic/baselines
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fixe tests of test_env_after_learn

Browse Source
This commit is contained in:
Peter Zhokhov
2018-09-10 10:32:42 -07:00
parent 58b1021b28
commit 59a7ffb84d
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
baselines/common/tests/test_env_after_learn.py
View File

@@ -12,17 +12,17 @@ algos = ['a2c', 'acer', 'acktr', 'deepq', 'ppo2', 'trpo_mpi']
@pytest.mark.parametrize('algo', algos) @pytest.mark.parametrize('algo', algos)
def test_env_after_learn(algo): def test_env_after_learn(algo):
def make_env(): def make_env():
env = gym.make('PongNoFrameskip-v4') # acktr requires too much RAM, fails on travis
env = gym.make('CartPole-v1' if algo == 'acktr' else 'PongNoFrameskip-v4')
return env return env
make_session(make_default=True, graph=tf.Graph()) make_session(make_default=True, graph=tf.Graph())
env = SubprocVecEnv([make_env]) env = SubprocVecEnv([make_env])
learn = get_learn_function(algo) learn = get_learn_function(algo)
network = cnn(one_dim_bias=True)
# Commenting out the following line resolves the issue, though crash happens at env.reset(). # Commenting out the following line resolves the issue, though crash happens at env.reset().
learn(network=network, env=env, total_timesteps=0, load_path=None, seed=None) learn(network='mlp', env=env, total_timesteps=0, load_path=None, seed=None)
env.reset() env.reset()
env.close() env.close()