get rid of unnecessary variables

philtabor · Nov 3, 2020 · ba997f7 · ba997f7
1 parent 278a21a
commit ba997f7
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 9 deletions.
diff --git a/ReinforcementLearning/PolicyGradient/DDPG/tensorflow2/pendulum/ddpg_tf2.py b/ReinforcementLearning/PolicyGradient/DDPG/tensorflow2/pendulum/ddpg_tf2.py
@@ -6,14 +6,15 @@
 from networks import ActorNetwork, CriticNetwork
 
 class Agent:
-    def __init__(self, alpha=0.001, beta=0.002, input_dims=[8], env=None,
+    def __init__(self, input_dims, alpha=0.001, beta=0.002, env=None,
             gamma=0.99, n_actions=2, max_size=1000000, tau=0.005, 
-            fc1=512, fc2=512, batch_size=64):
+            fc1=400, fc2=300, batch_size=64, noise=0.1):
         self.gamma = gamma
         self.tau = tau
         self.memory = ReplayBuffer(max_size, input_dims, n_actions)
         self.batch_size = batch_size
         self.n_actions = n_actions
+        self.noise = noise
         self.max_action = env.action_space.high[0]
         self.min_action = env.action_space.low[0]
 
@@ -67,7 +68,7 @@ def choose_action(self, observation, evaluate=False):
         actions = self.actor(state)
         if not evaluate:
             actions += tf.random.normal(shape=[self.n_actions],
-                    mean=0.0, stddev=0.1)
+                    mean=0.0, stddev=self.noise)
         # note that if the environment has an action > 1, we have to multiply by
         # max action at some point
         actions = tf.clip_by_value(actions, self.min_action, self.max_action)
@@ -110,7 +111,3 @@ def learn(self):
             actor_network_gradient, self.actor.trainable_variables))
 
         self.update_network_parameters()
-
-
-
-
diff --git a/ReinforcementLearning/PolicyGradient/DDPG/tensorflow2/pendulum/networks.py b/ReinforcementLearning/PolicyGradient/DDPG/tensorflow2/pendulum/networks.py
@@ -4,12 +4,11 @@
 from tensorflow.keras.layers import Dense
 
 class CriticNetwork(keras.Model):
-    def __init__(self, n_actions, fc1_dims=512, fc2_dims=512,
+    def __init__(self, fc1_dims=512, fc2_dims=512,
             name='critic', chkpt_dir='tmp/ddpg'):
         super(CriticNetwork, self).__init__()
         self.fc1_dims = fc1_dims
         self.fc2_dims = fc2_dims
-        self.n_actions = n_actions
 
         self.model_name = name
         self.checkpoint_dir = chkpt_dir