gym-examples 2.0.52__py3-none-any.whl → 2.0.54__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "2.0.52"
+__version__ = "2.0.54"

gym_examples/envs/wsn_env.py

@@ -117,15 +117,16 @@ class WSNRoutingEnv(gym.Env):
             # final_reward = net(rewards_individual)
             final_reward = np.sum(rewards[i]) 
             rewards[i] = final_reward
-
+        print("\n=================================================")
+        print(f"Rewards: {[[rewards[i], self.network_reward_consumption_energy(), self.network_reward_dispersion_remaining_energy()] for i in range(self.n_sensors)]}")
         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]
-
+        print("==================================================\n")
         for i in range(self.n_sensors):
             if (self.remaining_energy[i] <= 0) or (self.number_of_packets[i] <= 0):
                 dones[i] = True
 
         # Integrate the mobility of the sensors
-        self.integrate_mobility() 
+        # self.integrate_mobility() 
 
         self.distance_to_base = np.linalg.norm(self.sensor_positions - base_station_position, axis=1)
 
@@ -217,7 +218,8 @@ class WSNRoutingEnv(gym.Env):
         max_transmission_energy = self.transmission_energy(self.n_sensors * initial_number_of_packets, self.coverage_radius)
         max_reception_energy = self.reception_energy(self.n_sensors * initial_number_of_packets)
         max_total_energy = max_transmission_energy + max_reception_energy
-        normalized_total_energy = total_energy / max_total_energy
+        # normalized_total_energy = total_energy / max_total_energy
+        normalized_total_energy = transmission_energy / max_transmission_energy
 
         return np.clip(1 - normalized_total_energy, 0, 1)
     

{gym_examples-2.0.52.dist-info → gym_examples-2.0.54.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 2.0.52
+Version: 2.0.54
 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-2.0.54.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=47b1oSeurLM2pmSSFWOx-FDfw1qfyNKguLyyNpysyiw,193
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=dO2nPz444_2A1T6gKxNd9q03K2AI26zTt9_kzzvZ-9g,15390
+gym_examples-2.0.54.dist-info/METADATA,sha256=Av7RM4iEj2AkOiPyWbR9QcrUMitTtj8E8HbTTqJJkVo,411
+gym_examples-2.0.54.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-2.0.54.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-2.0.54.dist-info/RECORD,,

gym_examples-2.0.52.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=6aaeH8rkfL_LI7cvWeIw12KjsNXo-mMyDfYWUedc1AU,193
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=0B3NR4ovrgafYv1oIm-EG_tnReB965W5QICY7rQnKVk,14999
-gym_examples-2.0.52.dist-info/METADATA,sha256=kZ8UE_UTc9Qyoo82ZMIyZWBMCRLtBvRcup6mKDBSbcE,411
-gym_examples-2.0.52.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-2.0.52.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-2.0.52.dist-info/RECORD,,