gym-examples 3.0.756__py3-none-any.whl → 3.0.758__py3-none-any.whl

gym_examples/__init__.py

@@ -5,4 +5,4 @@ register(
      entry_point="gym_examples.envs:WSNRoutingEnv",
 )
 
-__version__ = "3.0.756"
+__version__ = "3.0.758"

gym_examples/envs/wsn_env.py

@@ -51,8 +51,8 @@ class ScalarAttentionModel(nn.Module):
         scalar_output = self.output_layer(attention_output)
         return scalar_output
 
-# net = ScalarAttentionModel(input_dim)
-# net = net.double()  # Convert the weights to Double
+net = ScalarAttentionModel(input_dim)
+net = net.double()  # Convert the weights to Double
 
 class WSNRoutingEnv(gym.Env):
 
@@ -212,7 +212,7 @@ class WSNRoutingEnv(gym.Env):
                 
             self.number_of_packets[i] = 0 # Reset the number of packets of the sensor i
             # Calculate final reward
-            # rewards[i] = self.compute_attention_rewards(rewards[i])
+            rewards[i] = self.compute_attention_rewards(rewards[i])
             # rewards[i] = np.mean(rewards[i])
         
         # Integrate the mobility of the sensors
@@ -226,10 +226,7 @@ class WSNRoutingEnv(gym.Env):
         self.get_metrics()
 
         # rewards = [reward.item() if isinstance(reward, torch.Tensor) else reward for reward in rewards] # Convert the reward to a float
-        
-        rewards = self.compute_attention_rewards(rewards, self.n_sensors)
-        print(f"Rewards: {rewards}")
-        # rewards = np.mean(rewards)
+        rewards = np.mean(rewards)
 
         for i in range(self.n_sensors):
             if not dones[i]:
@@ -466,20 +463,14 @@ class WSNRoutingEnv(gym.Env):
         return np.clip(normalized_throughput, 0, 1)
     
 
-    def compute_attention_rewards(self, rewards, n_sensors):
+    def compute_attention_rewards(self, reward):
         '''
         Compute the attention-based rewards
         '''
-        net = ScalarAttentionModel(n_sensors)
-        net = net.double()  # Convert the weights to Double
-        final_reward = []
-        for i in range(len(rewards[0])):
-            rewards_i = [reward[i] for reward in rewards]
-            rewards_i = torch.tensor(rewards_i, dtype=torch.double)
-            rewards_i = rewards_i.unsqueeze(0) # Add batch dimension
-            final_reward.append(net(rewards_i).item())
+        rewards_i = torch.tensor(reward, dtype=torch.double)
+        rewards_i = rewards_i.unsqueeze(0) # Add batch dimension
         
-        return np.mean(final_reward) 
+        return np.mean(net(rewards_i).item()) 
 
 
     # def compute_attention_reward(self, rewards):

{gym_examples-3.0.756.dist-info → gym_examples-3.0.758.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.756
+Version: 3.0.758
 Summary: A custom environment for multi-agent reinforcement learning focused on WSN routing.
 Home-page: https://github.com/gedji/CODES.git
 Author: Georges Djimefo

gym_examples-3.0.758.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=f70ODc3g1vDL3YyDihgU_517hCz3Vcr6WxdqCFajnvM,166
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=v3XsnNUpmtjIGDHR9iOWRQJsVEnbv7qyxWOlJ1_H55A,26558
+gym_examples-3.0.758.dist-info/METADATA,sha256=eUk0935bbVmyaBfSmUNA5YLhtONmtxJ1TCvgDlzG9JE,412
+gym_examples-3.0.758.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.758.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.758.dist-info/RECORD,,

gym_examples-3.0.756.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=4C-dUiI0EI9rNFua-VrPKyk7hyZgishTEyhirm0iCnY,166
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=YUK-nwlyXttjds6OmBvOTirF9yskrVNzSmI3e_5_8fI,26995
-gym_examples-3.0.756.dist-info/METADATA,sha256=yx3aFTcjtAKIzw_5IU9gV2UoMQaVeI85-4Hn6Kngj6Q,412
-gym_examples-3.0.756.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.756.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.756.dist-info/RECORD,,