gym-examples 3.0.36__py3-none-any.whl → 3.0.38__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "3.0.36"
+__version__ = "3.0.38"

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 = 4  # lenght of the individual rewards vector
+input_dim = 6  # lenght of the individual rewards vector
 output_dim = 1  # final reward
 
 Eelec = 50e-9  # energy consumption per bit in joules
@@ -146,6 +146,9 @@ class WSNRoutingEnv(gym.Env):
 
                 # Compute individual rewards
                 rewards[i] = self.compute_individual_rewards(i, action)
+                reward_packet_delivery_ratio = self.compute_reward_packet_delivery_ratio()
+                reward_latency = self.compute_reward_latency()
+                rewards[i] = np.append(rewards[i], [reward_packet_delivery_ratio, reward_latency])
                 # Update the number of packets
                 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
@@ -165,11 +168,11 @@ class WSNRoutingEnv(gym.Env):
 
         self.get_metrics()
 
-        reward_packet_delivery_ratio = self.compute_reward_packet_delivery_ratio()
-        reward_latency = self.compute_reward_latency()
-        rewards_metrics = [reward_packet_delivery_ratio, reward_latency]
-        rewards_metrics = self.compute_attention_rewards(rewards_metrics)
-        rewards = [torch.tensor(r, dtype=torch.float64) + rewards_metrics if isinstance(r, int) else r + rewards_metrics for r in rewards]
+        # reward_packet_delivery_ratio = self.compute_reward_packet_delivery_ratio()
+        # reward_latency = self.compute_reward_latency()
+        # rewards_metrics = [reward_packet_delivery_ratio, reward_latency]
+        # rewards_metrics = self.compute_attention_rewards(rewards_metrics)
+        # rewards = [torch.tensor(r, dtype=torch.float64) + rewards_metrics if isinstance(r, int) else r + rewards_metrics for r in rewards]
 
         return self._get_obs(), rewards, dones, {}
 

{gym_examples-3.0.36.dist-info → gym_examples-3.0.38.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.36
+Version: 3.0.38
 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-3.0.38.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=286-MtnDt-9kaoNC_GYG3ThCFajThGP6oSNFDSf8dR4,193
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=xkG40uqGVb7b5HeWjhaoRi2O6k3qOyn0bpa_rajCxYs,19238
+gym_examples-3.0.38.dist-info/METADATA,sha256=E5UKSrZDkqKJaoyVUYOP3xGKubRN1Kfm7NQ1VEicvQ4,411
+gym_examples-3.0.38.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.38.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.38.dist-info/RECORD,,

gym_examples-3.0.36.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=VS6xQR_7oWFS7m3DMHmBZBaaXseH1lDWbgiMiYtfY1Q,193
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=TBiED0ZrMLUclCOcsZwYnP_ecl3KQEYGAeqTfkYke8U,18972
-gym_examples-3.0.36.dist-info/METADATA,sha256=iXEHSv-wwCpXBqwTlWAkmNfn8jP2QCWpxFE2AgGxmhI,411
-gym_examples-3.0.36.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.36.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.36.dist-info/RECORD,,