gym-examples 3.0.220__py3-none-any.whl → 3.0.221__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "3.0.220"
+__version__ = "3.0.221"

gym_examples/envs/wsn_env.py

@@ -213,37 +213,37 @@ class WSNRoutingEnv(gym.Env):
 
         rewards = [r.item() if isinstance(r, torch.Tensor) else r for r in rewards] # Convert the rewards to a list of floats
         # rewards = np.sum(rewards)  # Sum the rewards of all agents
-        # rewards = np.mean(rewards)  # Average the rewards of all agents
-        rewards = np.mean(self.compute_network_rewards())  # Average the rewards of all agents
+        rewards = np.mean(rewards)  # Average the rewards of all agents
+        # rewards = np.mean(self.compute_network_rewards())  # Average the rewards of all agents
         # print(f"Step: {self.steps}, Rewards: {rewards}, Done: {dones}")
         dones = all(dones)  # Done if all agents are done
         
-        if os.getenv('PRINT_STATS') == 'True': # We are trying to extract only the statistics for the PPO algorithm
-            self.number_of_steps += 1
-            self.episode_return += rewards
-            if self.number_of_steps >= self.num_timesteps:
-                self.episode_returns.append(self.episode_return)
-                self.episode_std_remaining_energy.append(np.std(self.remaining_energy))
-                self.episode_mean_remaining_energy.append(np.mean(self.remaining_energy))
-                self.episode_total_consumption_energy.append(np.sum(initial_energy - self.remaining_energy))
-                self.episode_network_throughput.append(self.network_throughput)
-                self.episode_packet_delivery_ratio.append(self.packet_delivery_ratio)
-                self.episode_network_lifetime.append(self.network_lifetime)
-                self.episode_average_latency.append(self.average_latency)
-
-                metrics = {
-                    "returns_PPO": self.episode_returns,
-                    "std_remaining_energy_PPO": self.episode_std_remaining_energy,
-                    "total_consumption_energy_PPO": self.episode_total_consumption_energy,
-                    "mean_remaining_energy_PPO": self.episode_mean_remaining_energy,
-                    "network_throughput_PPO": self.episode_network_throughput,
-                    "packet_delivery_ratio_PPO": self.episode_packet_delivery_ratio,
-                    "network_lifetime_PPO": self.episode_network_lifetime,
-                    "average_latency_PPO": self.episode_average_latency
-                }
-
-                for metric_name, metric_value in metrics.items():
-                    np.save(f"{base_back_up_dir}{metric_name}_{self.version}.npy", np.array(metric_value))
+        # if os.getenv('PRINT_STATS') == 'True': # We are trying to extract only the statistics for the PPO algorithm
+        #     self.number_of_steps += 1
+        #     self.episode_return += rewards
+        #     if self.number_of_steps >= self.num_timesteps:
+        #         self.episode_returns.append(self.episode_return)
+        #         self.episode_std_remaining_energy.append(np.std(self.remaining_energy))
+        #         self.episode_mean_remaining_energy.append(np.mean(self.remaining_energy))
+        #         self.episode_total_consumption_energy.append(np.sum(initial_energy - self.remaining_energy))
+        #         self.episode_network_throughput.append(self.network_throughput)
+        #         self.episode_packet_delivery_ratio.append(self.packet_delivery_ratio)
+        #         self.episode_network_lifetime.append(self.network_lifetime)
+        #         self.episode_average_latency.append(self.average_latency)
+
+        #         metrics = {
+        #             "returns_PPO": self.episode_returns,
+        #             "std_remaining_energy_PPO": self.episode_std_remaining_energy,
+        #             "total_consumption_energy_PPO": self.episode_total_consumption_energy,
+        #             "mean_remaining_energy_PPO": self.episode_mean_remaining_energy,
+        #             "network_throughput_PPO": self.episode_network_throughput,
+        #             "packet_delivery_ratio_PPO": self.episode_packet_delivery_ratio,
+        #             "network_lifetime_PPO": self.episode_network_lifetime,
+        #             "average_latency_PPO": self.episode_average_latency
+        #         }
+
+        #         for metric_name, metric_value in metrics.items():
+        #             np.save(f"{base_back_up_dir}{metric_name}_{self.version}.npy", np.array(metric_value))
 
         return self._get_obs(), rewards, dones, {}
 
@@ -387,7 +387,7 @@ class WSNRoutingEnv(gym.Env):
         rewards_performance = np.array([reward_latency, reward_network_throughput, reward_packet_delivery_ratio])
     
         return np.concatenate((rewards_energy, rewards_performance))
-        # return rewards_energy
+    
 
     def compute_network_rewards(self):
 
@@ -400,9 +400,7 @@ class WSNRoutingEnv(gym.Env):
         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))
-        # return rewards_energy
-        return np.array([reward_consumption_energy])
+        return np.concatenate((rewards_energy, rewards_performance))
 
     def network_reward_dispersion_remaining_energy(self):
         '''

{gym_examples-3.0.220.dist-info → gym_examples-3.0.221.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.220
+Version: 3.0.221
 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-3.0.221.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=e3IzKZG7FDVeQeid5naFn1PzaMlIKk94FSEIIRc4DOk,194
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=9QXOPbuHBEAA4X24dYgYRWQdayupNxTv_Pmyh6PzmRk,26254
+gym_examples-3.0.221.dist-info/METADATA,sha256=geg1ENQ3KH6mdK_BF8opzQPDwil7KcCp-OXBsbrIP-8,412
+gym_examples-3.0.221.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.221.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.221.dist-info/RECORD,,

gym_examples-3.0.220.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=MEYnbGONT9nEeGjf_5eFPpnFuoYOFSHCwbl4ZhogWlo,194
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=KaqAWRQ9hG_Q46r60GwUu0p92D9lWcRwOerHHRP9CXo,26322
-gym_examples-3.0.220.dist-info/METADATA,sha256=iM7DTB1bT5TB-MkxbZcm9wf_8hFrLgrOVRgzTmYRENU,412
-gym_examples-3.0.220.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.220.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.220.dist-info/RECORD,,