[ci skip] Doc fix

DeepQ -> DQN

README.md

@@ -125,7 +125,7 @@ All the following examples can be executed online using Google colab notebooks:
 | ACER                | :heavy_check_mark:           | :heavy_check_mark: | :x: <sup>(5)</sup> | :heavy_check_mark: | :x:                 | :x:                | :heavy_check_mark:                |
 | ACKTR               | :heavy_check_mark:           | :heavy_check_mark: | :x: <sup>(5)</sup> | :heavy_check_mark: | :x:                 | :x:                | :heavy_check_mark:                |
 | DDPG                | :heavy_check_mark:           | :x:                | :heavy_check_mark: | :x:                | :x:                 | :x:                | :x:                               |
-| DeepQ               | :heavy_check_mark:           | :x:                | :x:                | :heavy_check_mark: | :x:                 | :x:                | :x:                               |
+| DQN                 | :heavy_check_mark:           | :x:                | :x:                | :heavy_check_mark: | :x:                 | :x:                | :x:                               |
 | GAIL <sup>(2)</sup> | :heavy_check_mark:           | :heavy_check_mark: | :heavy_check_mark: | :x:                | :x:                 | :x:                | :heavy_check_mark: <sup>(4)</sup> |
 | HER <sup>(3)</sup>  | :x: <sup>(5)</sup>           | :x:                | :heavy_check_mark: | :x:                | :x:                 | :x:                | :x:                               |
 | PPO1                | :heavy_check_mark:           | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark: | :heavy_check_mark:  | :heavy_check_mark: | :heavy_check_mark: <sup>(4)</sup> |

docs/modules/dqn.rst

@@ -58,7 +58,7 @@ Example
 
   del model # remove to demonstrate saving and loading
 
-  DeepQ.load("deepq_cartpole")
+  DQN.load("deepq_cartpole")
 
   obs = env.reset()
   while True:

stable_baselines/deepq/__init__.py

@@ -6,7 +6,7 @@
 
 def wrap_atari_dqn(env):
     """
-    wrap the environment in atari wrappers for DeepQ
+    wrap the environment in atari wrappers for DQN
 
     :param env: (Gym Environment) the environment
     :return: (Gym Environment) the wrapped environment

stable_baselines/deepq/build_graph.py

@@ -126,7 +126,7 @@ def build_act(q_func, ob_space, ac_space, stochastic_ph, update_eps_ph, sess):
     """
     Creates the act function:
 
-    :param q_func: (DeepQPolicy) the policy
+    :param q_func: (DQNPolicy) the policy
     :param ob_space: (Gym Space) The observation space of the environment
     :param ac_space: (Gym Space) The action space of the environment
     :param stochastic_ph: (TensorFlow Tensor) the stochastic placeholder
@@ -166,7 +166,7 @@ def build_act_with_param_noise(q_func, ob_space, ac_space, stochastic_ph, update
     """
     Creates the act function with support for parameter space noise exploration (https://arxiv.org/abs/1706.01905):
 
-    :param q_func: (DeepQPolicy) the policy
+    :param q_func: (DQNPolicy) the policy
     :param ob_space: (Gym Space) The observation space of the environment
     :param ac_space: (Gym Space) The action space of the environment
     :param stochastic_ph: (TensorFlow Tensor) the stochastic placeholder
@@ -324,7 +324,7 @@ def build_train(q_func, ob_space, ac_space, optimizer, sess, grad_norm_clipping=
     """
     Creates the train function:
 
-    :param q_func: (DeepQPolicy) the policy
+    :param q_func: (DQNPolicy) the policy
     :param ob_space: (Gym Space) The observation space of the environment
     :param ac_space: (Gym Space) The action space of the environment
     :param reuse: (bool) whether or not to reuse the graph variables

stable_baselines/deepq/dqn.py

@@ -15,7 +15,7 @@ class DQN(OffPolicyRLModel):
     """
     The DQN model class. DQN paper: https://arxiv.org/pdf/1312.5602.pdf
 
-    :param policy: (DeepQPolicy or str) The policy model to use (MlpPolicy, CnnPolicy, LnMlpPolicy, ...)
+    :param policy: (DQNPolicy or str) The policy model to use (MlpPolicy, CnnPolicy, LnMlpPolicy, ...)
     :param env: (Gym environment or str) The environment to learn from (if registered in Gym, can be str)
     :param gamma: (float) discount factor
     :param learning_rate: (float) learning rate for adam optimizer

stable_baselines/deepq/experiments/custom_cartpole.py

@@ -21,7 +21,7 @@ def __init__(self, *args, **kwargs):
 
 def main(args):
     """
-    Train a DeepQ agent on cartpole env
+    Train a DQN agent on cartpole env
     :param args: (Parsed Arguments) the input arguments
     """
     with tf_utils.make_session(8) as sess:
@@ -99,5 +99,3 @@ def main(args):
                         help="Maximum number of timesteps when not rendering")
     args = parser.parse_args()
     main(args)
-
-

stable_baselines/deepq/experiments/enjoy_mountaincar.py

@@ -7,7 +7,7 @@
 
 def main(args):
     """
-    run a trained model for the mountain car problem
+    Run a trained model for the mountain car problem
 
     :param args: (ArgumentParser) the input arguments
     """

stable_baselines/deepq/experiments/enjoy_pong.py

@@ -6,7 +6,7 @@
 
 def main():
     """
-    run a trained model for the pong problem
+    Run a trained model for the pong problem
     """
     env = gym.make("PongNoFrameskip-v4")
     env = deepq.wrap_atari_dqn(env)

stable_baselines/deepq/experiments/run_atari.py

@@ -8,7 +8,7 @@
 
 def main():
     """
-    run the atari test
+    Run the atari test
     """
     parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument('--env', help='environment ID', default='BreakoutNoFrameskip-v4')

stable_baselines/deepq/experiments/train_cartpole.py

@@ -8,7 +8,7 @@
 
 def callback(lcl, _glb):
     """
-    the callback function for logging and saving
+    The callback function for logging and saving
 
     :param lcl: (dict) the local variables
     :param _glb: (dict) the global variables
@@ -25,7 +25,7 @@ def callback(lcl, _glb):
 
 def main(args):
     """
-    train and save the DeepQ model, for the cartpole problem
+    Train and save the DQN model, for the cartpole problem
 
     :param args: (ArgumentParser) the input arguments
     """

stable_baselines/deepq/experiments/train_mountaincar.py

@@ -16,7 +16,7 @@ def __init__(self, *args, **kwargs):
 
 def main(args):
     """
-    train and save the DeepQ model, for the mountain car problem
+    Train and save the DQN model, for the mountain car problem
 
     :param args: (ArgumentParser) the input arguments
     """