gym-examples 3.0.224__py3-none-any.whl → 3.0.226__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "3.0.224"
+__version__ = "3.0.226"

gym_examples/envs/wsn_env.py

@@ -11,7 +11,7 @@ import torch.nn.functional as F
 import os
 
 # Define the network parameters for the final reward function
-input_dim = 2  # length of the individual rewards vector
+input_dim = 7  # length of the individual rewards vector
 output_dim = 1  # final reward
 
 Eelec = 50e-9  # energy consumption per bit in joules
@@ -166,8 +166,8 @@ class WSNRoutingEnv(gym.Env):
                 self.packet_latency[i] = 0
 
                 # rewards[i] = self.compute_individual_rewards(i, action)
-                # rewards[i] = np.ones(input_dim) * max_reward # Reward for transmitting data to the base station
-                rewards[i] = np.ones(input_dim) # Reward for transmitting data to the base station
+                rewards[i] = np.ones(input_dim) * max_reward # Reward for transmitting data to the base station
+                # rewards[i] = np.ones(input_dim) # Reward for transmitting data to the base station
                 dones[i] = True       
             else:
                 distance = np.linalg.norm(self.sensor_positions[i] - self.sensor_positions[action])
@@ -391,8 +391,8 @@ 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 np.array([reward_consumption_energy, reward_dispersion_remaining_energy])
+        return np.concatenate((rewards_energy, rewards_performance))
+        # return np.array([reward_consumption_energy, reward_dispersion_remaining_energy])
     
 
     def compute_network_rewards(self):

{gym_examples-3.0.224.dist-info → gym_examples-3.0.226.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.224
+Version: 3.0.226
 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-3.0.226.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=zblH-5_lZeAcLQ1-3_KytHVwJby79q4zDmuRKoU_oLg,194
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=ZozBJYjlKTdIozRpK-hEvHT4MSAQcwFKgb4NFTwpDIA,26381
+gym_examples-3.0.226.dist-info/METADATA,sha256=j2HVG5AGoZNI5RyiGrw1s_5VKdeFSIT87BYttXiqbA4,412
+gym_examples-3.0.226.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.226.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.226.dist-info/RECORD,,

gym_examples-3.0.224.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=O3Do7Y6dV9a8VGxnVg0jOzmDPuyv0ISI_7DQcCG8Ihs,194
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=ykllANFl8ORgtX7T9HgcIgsnsAW-2bH0wxk-5tWu0Ng,26381
-gym_examples-3.0.224.dist-info/METADATA,sha256=2TY7rpy6ZJpqn7-jkVnfLsPekbtOoTmJdk1miX5Ckk8,412
-gym_examples-3.0.224.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.224.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.224.dist-info/RECORD,,