gym-examples 3.0.40__py3-none-any.whl → 3.0.42__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "3.0.40"
+__version__ = "3.0.42"

gym_examples/envs/wsn_env.py

@@ -10,7 +10,7 @@ import torch.nn as nn
 import torch.nn.functional as F
 
 # Define the network parameters for the final reward function
-input_dim = 6  # lenght of the individual rewards vector
+input_dim = 4  # lenght of the individual rewards vector
 output_dim = 1  # final reward
 
 Eelec = 50e-9  # energy consumption per bit in joules
@@ -153,8 +153,8 @@ class WSNRoutingEnv(gym.Env):
                 self.number_of_packets[action] += self.number_of_packets[i]
             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[i] = self.compute_sum_rewards(rewards[i])
+            rewards[i] = self.compute_attention_rewards(rewards[i])
+            # rewards[i] = self.compute_sum_rewards(rewards[i])
         for i in range(self.n_sensors):
             if (self.remaining_energy[i] <= 0) or (self.number_of_packets[i] <= 0):
                 dones[i] = True
@@ -301,7 +301,8 @@ class WSNRoutingEnv(gym.Env):
         reward_dispersion_remaining_energy = self.compute_reward_dispersion_remaining_energy()
         reward_number_of_packets = self.compute_reward_number_of_packets(action)
 
-        return [reward_angle, reward_consumption_energy, reward_dispersion_remaining_energy, reward_number_of_packets]
+        # return [reward_angle, reward_consumption_energy, reward_dispersion_remaining_energy, reward_number_of_packets]
+        return [reward_consumption_energy, reward_dispersion_remaining_energy]
         
     def network_reward_dispersion_remaining_energy(self):
         '''

{gym_examples-3.0.40.dist-info → gym_examples-3.0.42.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.40
+Version: 3.0.42
 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-3.0.42.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=kLTFJhJe48NKPRenv6nTfwR9FbFVrCMz4hzeIhHTrgI,193
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=P3-MHflhQ29pLwrDb2oY7NjJvbpDXuTz6bPX2_mbqPQ,19522
+gym_examples-3.0.42.dist-info/METADATA,sha256=T4wmhIiKxlhX7Mccah7D-kCaZap2pgJPtrVgyo0rMPI,411
+gym_examples-3.0.42.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.42.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.42.dist-info/RECORD,,

gym_examples-3.0.40.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=RAJJmbqLaH4xxUvVUvfFFeXvEHl2bo2r_zLkqr9TUAg,193
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=k5yJgvCEMrizm8ZZOpukLRVcnAMTnYWP_ri8nnG9KYc,19440
-gym_examples-3.0.40.dist-info/METADATA,sha256=bLu5N3z4h-SRmD_CelwNmWuJGT6mcxJ9Hqyhz6aeQ8o,411
-gym_examples-3.0.40.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.40.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.40.dist-info/RECORD,,