add code coverage report

.benchmark_pattern

@@ -1 +1 @@
-ppo2
+

.gitignore

@@ -5,6 +5,7 @@
 .pytest_cache
 .DS_Store
 .idea
+.coverage
 
 # Setuptools distribution and build folders.
 /dist/

README.md

@@ -139,3 +139,4 @@ To cite this repository in publications:
       journal = {GitHub repository},
       howpublished = {\url{https://github.com/openai/baselines}},
     }
+

baselines/common/atari_wrappers.py

@@ -156,7 +156,7 @@ class FrameStack(gym.Wrapper):
         self.k = k
         self.frames = deque([], maxlen=k)
         shp = env.observation_space.shape
-        self.observation_space = spaces.Box(low=0, high=255, shape=(shp[0], shp[1], shp[2] * k), dtype=np.uint8)
+        self.observation_space = spaces.Box(low=0, high=255, shape=(shp[0], shp[1], shp[2] * k), dtype=env.observation_space.dtype)
 
     def reset(self):
         ob = self.env.reset()
@@ -176,6 +176,7 @@ class FrameStack(gym.Wrapper):
 class ScaledFloatFrame(gym.ObservationWrapper):
     def __init__(self, env):
         gym.ObservationWrapper.__init__(self, env)
+        self.observation_space = gym.spaces.Box(low=0, high=1, shape=env.observation_space.shape, dtype=np.float32)
 
     def observation(self, observation):
         # careful! This undoes the memory optimization, use

baselines/common/models.py

@@ -138,7 +138,7 @@ def conv_only(convs=[(32, 8, 4), (64, 4, 2), (64, 3, 1)], **conv_kwargs):
     '''
 
     def network_fn(X):
-        out = X
+        out = tf.cast(X, tf.float32) / 255.
         with tf.variable_scope("convnet"):
             for num_outputs, kernel_size, stride in convs:
                 out = layers.convolution2d(out,

setup.py

@@ -25,7 +25,8 @@ setup(name='baselines',
       extras_require={
         'test': [
             'filelock',
-            'pytest'
+            'pytest',
+            'pytest-cov',
         ]
       },
       description='OpenAI baselines: high quality implementations of reinforcement learning algorithms',