gym-examples 2.0.98__py3-none-any.whl → 2.0.101__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "2.0.98"
+__version__ = "2.0.101"

gym_examples/envs/wsn_env.py

@@ -135,7 +135,6 @@ class WSNRoutingEnv(gym.Env):
             # self.rewards_individual[i] = rewards[i]
             final_reward = np.sum(rewards[i]) 
             rewards[i] = final_reward
-
         # rewards = [0.5 * r + 0.5 * (1/self.n_sensors) * (self.network_reward_consumption_energy() + self.network_reward_dispersion_remaining_energy()) for r in rewards]
         # rewards = [0.5 * r + 0.5 * (self.network_reward_consumption_energy() + self.network_reward_dispersion_remaining_energy()) for r in rewards]
         
@@ -286,33 +285,32 @@ class WSNRoutingEnv(gym.Env):
         reward_dispersion_remaining_energy = self.compute_reward_dispersion_remaining_energy()
         reward_number_of_packets = self.compute_reward_number_of_packets(action)
 
-        # return [reward_angle, reward_distance, reward_consumption_energy, reward_dispersion_remaining_energy, reward_number_of_packets]
+        return [reward_angle, reward_distance, reward_consumption_energy, reward_dispersion_remaining_energy, reward_number_of_packets]
         # return [reward_angle, reward_distance, reward_consumption_energy, reward_number_of_packets]
         # return [reward_angle, reward_distance, reward_dispersion_remaining_energy, reward_number_of_packets]
         # return [reward_angle, reward_distance, reward_consumption_energy, reward_dispersion_remaining_energy]
-        return [reward_distance, reward_consumption_energy, reward_dispersion_remaining_energy]
 
-    # def network_reward_dispersion_remaining_energy(self):
-    #     '''
-    #     Compute the reward based on the standard deviation of the remaining energy at the network level
-    #     '''
-    #     dispersion_remaining_energy = np.std(self.remaining_energy)
-    #     # Normalize the standard deviation of the remaining energy
-    #     max_dispersion_remaining_energy = initial_energy / 2 # maximum standard deviation of the remaining energy if n_sensors is even
-    #     normalized_dispersion_remaining_energy = dispersion_remaining_energy / max_dispersion_remaining_energy
+    def network_reward_dispersion_remaining_energy(self):
+        '''
+        Compute the reward based on the standard deviation of the remaining energy at the network level
+        '''
+        dispersion_remaining_energy = np.std(self.remaining_energy)
+        # Normalize the standard deviation of the remaining energy
+        max_dispersion_remaining_energy = initial_energy / 2 # maximum standard deviation of the remaining energy if n_sensors is even
+        normalized_dispersion_remaining_energy = dispersion_remaining_energy / max_dispersion_remaining_energy
 
-    #     return np.clip(1 - normalized_dispersion_remaining_energy, 0, 1)
+        return np.clip(1 - normalized_dispersion_remaining_energy, 0, 1)
     
-    # def network_reward_consumption_energy(self):
-    #     '''
-    #     Compute the reward based on the total energy consumption (transmission, reception) at the network level
-    #     '''
-    #     total_energy = self.n_sensors * initial_energy - np.sum(self.remaining_energy)
-    #     # Normalize the total energy consumption
-    #     max_total_energy = self.n_sensors * initial_energy
-    #     normalized_total_energy = total_energy / max_total_energy
+    def network_reward_consumption_energy(self):
+        '''
+        Compute the reward based on the total energy consumption (transmission, reception) at the network level
+        '''
+        total_energy = self.n_sensors * initial_energy - np.sum(self.remaining_energy)
+        # Normalize the total energy consumption
+        max_total_energy = self.n_sensors * initial_energy
+        normalized_total_energy = total_energy / max_total_energy
 
-    #     return np.clip(1 - normalized_total_energy, 0, 1)
+        return np.clip(1 - normalized_total_energy, 0, 1)
 
     def integrate_mobility(self):
         '''

{gym_examples-2.0.98.dist-info → gym_examples-2.0.101.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 2.0.98
+Version: 2.0.101
 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-2.0.101.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=eZO_an4Ddj18Zw0LMd1ZNXyurLLujaT6-H45paeHudA,194
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=VIHeF9hoBoYYxiGN9W0Na2kVYYGLlwc66O-pC6X_GTs,17214
+gym_examples-2.0.101.dist-info/METADATA,sha256=xABVZIeCirDgUEyFTgQYlzZzTGEtfyzhxJcL8qH9hVI,412
+gym_examples-2.0.101.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-2.0.101.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-2.0.101.dist-info/RECORD,,

gym_examples-2.0.98.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=ORPaAk46ppx34i0A3omNhSm2vpJlts0_2ctV7Vnheeo,193
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=ETRV1OEBIADxTIvej9qHoINig9r6LIqFUVRycPzy-mU,17351
-gym_examples-2.0.98.dist-info/METADATA,sha256=921iJigPx_7zXGxVbXD8dD3Ig8sqtT-RCDE02QbkFCI,411
-gym_examples-2.0.98.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-2.0.98.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-2.0.98.dist-info/RECORD,,