gym-examples 3.0.115__py3-none-any.whl → 3.0.116__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "3.0.115"
+__version__ = "3.0.116"

gym_examples/envs/wsn_env.py

@@ -64,7 +64,9 @@ class WSNRoutingEnv(gym.Env):
         )
         self.action_space = Tuple(tuple([Discrete(self.n_sensors + 1)] * self.n_agents))
                 
-        self.reset()        
+        self.reset()
+
+        self.episode_count = 0        
 
     def reset(self):                
         self.sensor_positions = np.random.rand(self.n_sensors, 2) * (upper_bound - lower_bound) + lower_bound
@@ -168,6 +170,8 @@ class WSNRoutingEnv(gym.Env):
 
         self.get_metrics()
 
+        # rewards = self.compute_network_rewards()
+
         return self._get_obs(), rewards, dones, {}
 
     def _get_obs(self):
@@ -312,7 +316,20 @@ class WSNRoutingEnv(gym.Env):
     
         return np.concatenate((rewards_energy, rewards_performance))
         # return rewards_energy
-                
+
+    def compute_network_rewards(self):
+
+        reward_consumption_energy = self.network_reward_consumption_energy()
+        reward_dispersion_remaining_energy = self.network_reward_dispersion_remaining_energy()
+        rewards_energy = np.array([reward_consumption_energy, reward_dispersion_remaining_energy])
+
+        reward_latency = self.compute_reward_latency()
+        reward_network_throughput = self.compute_reward_network_throughput()
+        reward_packet_delivery_ratio = self.compute_reward_packet_delivery_ratio()        
+        rewards_performance = np.array([reward_latency, reward_network_throughput, reward_packet_delivery_ratio])
+
+        return np.concatenate((rewards_energy, rewards_performance))
+
     def network_reward_dispersion_remaining_energy(self):
         '''
         Compute the reward based on the standard deviation of the remaining energy at the network level

{gym_examples-3.0.115.dist-info → gym_examples-3.0.116.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.115
+Version: 3.0.116
 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-3.0.116.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=09z5Ln2_klc9N1PzBH7KMq9f_84BOOXU6jsoFyKP5V8,194
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=tCuaa3kAtzXd-EhWkRzGbfxw6A_v3jZ0U9OUBk9bcJ8,21567
+gym_examples-3.0.116.dist-info/METADATA,sha256=aLxV_ifcG2NU1Pvt9PodOJz7ozlMEx7uhPagASu683k,412
+gym_examples-3.0.116.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.116.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.116.dist-info/RECORD,,

gym_examples-3.0.115.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=4tutbZYDTaS04kfY-9VcMSXg5aYZvn5jWVUwXk7vzR8,194
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=XSRDyoJXewSwDBtHJJHGYarmWDbgX4qlG5HMVTeASTI,20762
-gym_examples-3.0.115.dist-info/METADATA,sha256=N8sjWFwvyZ1IYM0Axh4HcwIzJkhzJxsLY4s7-x7z2lY,412
-gym_examples-3.0.115.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.115.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.115.dist-info/RECORD,,