gym-examples 2.0.8__py3-none-any.whl → 2.0.10__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "2.0.8"
+__version__ = "2.0.10"

gym_examples/envs/wsn_env.py

@@ -47,7 +47,7 @@ net = net.double()  # Convert the weights to Double
 
 
 class WSNRoutingEnv(gym.Env):
-    def __init__(self, n_sensors = 10, coverage_radius=50):
+    def __init__(self, n_sensors = 30, coverage_radius=50):
 
         super(WSNRoutingEnv, self).__init__()
 
@@ -76,14 +76,11 @@ class WSNRoutingEnv(gym.Env):
         self.consumption_energy = np.zeros(self.n_sensors)
         self.number_of_packets = np.ones(self.n_sensors, dtype=int)  # Number of packets to transmit
         self.episode_count += 1
-        self.step_count = 0
         return self._get_obs()
 
     def step(self, actions):
-        print(f"Actions: {actions}")
         rewards = [0] * self.n_sensors
         dones = [False] * self.n_sensors
-        self.step_count += 1
         for i, action in enumerate(actions):
             
             if action not in range(self.n_sensors + 1):
@@ -119,9 +116,9 @@ class WSNRoutingEnv(gym.Env):
                 rewards[i] = self.compute_individual_rewards(i, action, neighbors_i, remaining_energy_before)
             self.number_of_packets[i] = 0 # Reset the number of packets of the sensor i
             # Calculate final reward
-            # rewards_individual = torch.tensor(rewards[i], dtype=torch.double)                
-            # final_reward = net(rewards_individual)
-            final_reward = sum(rewards[i])
+            rewards_individual = torch.tensor(rewards[i], dtype=torch.double)                
+            final_reward = net(rewards_individual)
+            # final_reward = sum(rewards[i])
             rewards[i] = final_reward
 
         for i in range(self.n_sensors):
@@ -129,7 +126,7 @@ class WSNRoutingEnv(gym.Env):
                 dones[i] = True
 
         # Integrate the mobility of the sensors
-        # self.integrate_mobility() 
+        self.integrate_mobility() 
 
         return self._get_obs(), rewards, dones, {}
 

{gym_examples-2.0.8.dist-info → gym_examples-2.0.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 2.0.8
+Version: 2.0.10
 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-2.0.10.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=Xv8KufaWTkDnJ2noVaDh4OFIlwTqFk5KrsxPDNtkDKM,193
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=Qc2oUPLVpbyEdBMHEhpxuBd-CcLHvfcIEV37WP2mkU0,15135
+gym_examples-2.0.10.dist-info/METADATA,sha256=YOCYFjDkD2d9uVAYmKQNDI3V-Ib_G-zPrSH_WrYcjGo,411
+gym_examples-2.0.10.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-2.0.10.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-2.0.10.dist-info/RECORD,,

gym_examples-2.0.8.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=fIbIs37EHyLkQTZ5Ms2Qa1NGVpG3opspoUbt_BgWriY,192
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=cpqNN2fOEBE-_w-E4stAPH1VLsxPlIGtoZVV3dHmvhU,15236
-gym_examples-2.0.8.dist-info/METADATA,sha256=XlQxAfb-C0awmiUAIbEmsli6nSJPMWGZiqJYl1y_UUk,410
-gym_examples-2.0.8.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-2.0.8.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-2.0.8.dist-info/RECORD,,