gym-examples 2.0.72__py3-none-any.whl → 2.0.74__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "2.0.72"
+__version__ = "2.0.74"

gym_examples/envs/wsn_env.py

@@ -108,12 +108,7 @@ class WSNRoutingEnv(gym.Env):
             if action == self.n_sensors:
                 # Calculate the energy consumption and remaining for transmitting data to the base station
                 transmission_energy = self.transmission_energy(self.number_of_packets[i], self.distance_to_base[i])
-                self.update_sensor_energies(i, transmission_energy) 
-                # if np.sum(self.consumption_energy) != 0:
-                #     print("\n=================================================")
-                #     print(f"Sensor {i} transmits {self.number_of_packets[i]} packets to the base station.")
-                #     print(f"Consumption energy: {np.sum(self.consumption_energy)}")
-                #     print("=================================================\n")
+                self.update_sensor_energies(i, transmission_energy)
                 rewards[i] = self.compute_individual_rewards(i, action)
                 dones[i] = True       
             else:
@@ -121,12 +116,7 @@ class WSNRoutingEnv(gym.Env):
                 transmission_energy = self.transmission_energy(self.number_of_packets[i], distance)
                 reception_energy = self.reception_energy(self.number_of_packets[i])
                 self.update_sensor_energies(i, transmission_energy)  
-                self.update_sensor_energies(action, reception_energy)  
-                # if np.sum(self.consumption_energy) != 0:
-                #     print("\n=================================================")
-                #     print(f"Sensor {i} transmits {self.number_of_packets[i]} packets to sensor {action}.")
-                #     print(f"Consumption energy: {np.sum(self.consumption_energy)}")
-                #     print("=================================================\n") 
+                self.update_sensor_energies(action, reception_energy) 
                 # Compute individual rewards
                 rewards[i] = self.compute_individual_rewards(i, action)
                 # Update the number of packets
@@ -144,12 +134,6 @@ class WSNRoutingEnv(gym.Env):
         
         # Call methods once and store results to avoid repeated calculations
         network_consumption_energy = self.network_reward_consumption_energy()
-        if np.sum(self.consumption_energy) != 0:
-            print("\n=================================================")
-            print(f"Total consumption energy: {np.sum(self.consumption_energy)}")
-            print(f"Network consumption energy: {network_consumption_energy}")
-            print(f"Network dispersion energy: {self.network_reward_dispersion_remaining_energy()}")
-            print("=================================================\n")
         network_dispersion_energy = self.network_reward_dispersion_remaining_energy()
         # Only proceed if network consumption energy is not zero to avoid unnecessary list comprehension
         if network_consumption_energy != 0:
@@ -317,14 +301,9 @@ class WSNRoutingEnv(gym.Env):
         Compute the reward based on the total energy consumption (transmission, reception) at the network level
         '''
         total_energy = np.sum(self.consumption_energy)
-        print(f"Inside network_reward_consumption_energy, total energy: {total_energy}")
         # Normalize the total energy consumption
-        max_transmission_energy = self.transmission_energy(self.n_sensors * initial_number_of_packets, self.coverage_radius)
-        print(f"Inside network_reward_consumption_energy, max transmission energy: {max_transmission_energy}")
-        max_reception_energy = self.reception_energy(self.n_sensors * initial_number_of_packets)
-        print(f"Inside network_reward_consumption_energy, max reception energy: {max_reception_energy}")
-        normalized_total_energy = total_energy / (max_transmission_energy + max_reception_energy)
-        print(f"Inside network_reward_consumption_energy, normalized total energy: {normalized_total_energy}")
+        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)
 

{gym_examples-2.0.72.dist-info → gym_examples-2.0.74.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 2.0.72
+Version: 2.0.74
 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-2.0.74.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=b6eULvkNLM9uMNqjXtAmWboWIPZ1ydCHLooKGpegjcA,193
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=nzkby8VP2ADq4CUebDExqQwElLjdpdMr-bfLiaXd1qc,16620
+gym_examples-2.0.74.dist-info/METADATA,sha256=IzDB951sQkhW7PDYOd2QWGJIJNnKzJSgg5NXhIWujBQ,411
+gym_examples-2.0.74.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-2.0.74.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-2.0.74.dist-info/RECORD,,

gym_examples-2.0.72.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=rTuZiKxgQrl6_lA1u6-ac60xg1CRFlJOlEX6GKSvEfk,193
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=SorBJOVj9Jz4x-VosrChGaaesorWcd7K-qJvwhIZFAA,18553
-gym_examples-2.0.72.dist-info/METADATA,sha256=6_b2HqQbQ_FccJaGcgcsDI2Z9LOFbPmuAdfXhRiBs3Q,411
-gym_examples-2.0.72.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-2.0.72.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-2.0.72.dist-info/RECORD,,