gym-examples 3.0.284__py3-none-any.whl → 3.0.286__py3-none-any.whl

gym_examples/__init__.py

@@ -5,4 +5,4 @@ register(
      entry_point="gym_examples.envs:WSNRoutingEnv",
 )
 
-__version__ = "3.0.284"
+__version__ = "3.0.286"

gym_examples/envs/wsn_env.py

@@ -81,10 +81,7 @@ class WSNRoutingEnv(gym.Env):
         )
 
         # self.action_space = Tuple(tuple([Discrete(self.n_sensors + 1)] * self.n_agents))
-        # self.action_space = MultiDiscrete([self.n_sensors + 1] * self.n_agents)
-        # self.action_space = MultiDiscrete([self.n_agents, self.n_sensors + 1]) 
-        # self.action_space = Discrete(self.n_sensors + 1)  # +1 for the base station
-        self.action_space = Discrete((self.n_sensors + 1)**self.n_agents)
+        self.action_space = MultiDiscrete([self.n_sensors + 1] * self.n_agents)
 
         self.reset()        
 
@@ -120,7 +117,6 @@ class WSNRoutingEnv(gym.Env):
         self.steps += 1 
         rewards = [-max_reward] * self.n_sensors
         dones = [False] * self.n_sensors
-        actions = self.to_base_n(actions, self.n_sensors + 1)
         for i, action in enumerate(actions):
             if self.remaining_energy[i] <= 0 or self.number_of_packets[i] <= 0:
                 continue  # Skip if sensor has no energy left or no packets to transmit
@@ -173,7 +169,7 @@ class WSNRoutingEnv(gym.Env):
                 self.packet_latency[action] += self.packet_latency[i] + latency_per_hop
                 self.packet_latency[i] = 0
 
-                rewards = self.compute_individual_rewards(i, action)  
+                rewards[i] = self.compute_individual_rewards(i, action) 
 
                 # Update the number of packets
                 self.number_of_packets[action] += self.number_of_packets[i]
@@ -181,7 +177,7 @@ class WSNRoutingEnv(gym.Env):
             self.number_of_packets[i] = 0 # Reset the number of packets of the sensor i
             # Calculate final reward
             # rewards[i] = self.compute_attention_rewards(rewards[i])
-            rewards = np.mean(rewards)
+            rewards[i] = np.mean(rewards[i])
         
         # Integrate the mobility of the sensors
         # self.integrate_mobility() 
@@ -194,9 +190,12 @@ class WSNRoutingEnv(gym.Env):
         self.get_metrics()
 
         rewards = [reward.item() if isinstance(reward, torch.Tensor) else reward for reward in rewards] # Convert the reward to a float
+        rewards = np.mean(rewards) # Average the rewards
+
         for i in range(self.n_sensors):
             if not dones[i]:
                 dones[i] = self.remaining_energy[i] <= 0 or self.number_of_packets[i] == 0
+        dones = np.all(dones)
 
         return self._get_obs(), rewards, dones, self.get_metrics()
 

{gym_examples-3.0.284.dist-info → gym_examples-3.0.286.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.284
+Version: 3.0.286
 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-3.0.286.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=1GK2OycRc394qAo5oxOKW-VdY8PGCGL8BGGeb7kYZmo,166
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=IxZOztoXNUFBhjzrZ_jw0nRg1EhPtTMYDOj6G2-ZT9U,23292
+gym_examples-3.0.286.dist-info/METADATA,sha256=Mu-PCSCgadaSrJI2QGlySSqtueil18a73qsvuIwyZxo,412
+gym_examples-3.0.286.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.286.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.286.dist-info/RECORD,,

gym_examples-3.0.284.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=SbYVbDAngXH8S9SM6aQijqGwMUt-FSXYtOV00-_0ahI,166
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=VzbARUwPIdS6-RkQND3dxx0lLheFpP6NqaBwT5JY91o,23503
-gym_examples-3.0.284.dist-info/METADATA,sha256=U9huJCLpn-NIXHhbpD97MFIY_WpCrOxX7ebSgLBsf_w,412
-gym_examples-3.0.284.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.284.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.284.dist-info/RECORD,,