gym-examples 3.0.728__py3-none-any.whl → 3.0.730__py3-none-any.whl

gym_examples/__init__.py

@@ -5,4 +5,4 @@ register(
      entry_point="gym_examples.envs:WSNRoutingEnv",
 )
 
-__version__ = "3.0.728"
+__version__ = "3.0.730"

gym_examples/envs/wsn_env.py

@@ -150,7 +150,8 @@ class WSNRoutingEnv(gym.Env):
         self.number_of_steps += 1
         self.steps += 1 
         # rewards = [-max_reward] * self.n_sensors
-        rewards = [[0] * input_dim] * self.n_sensors
+        reward_init = np.array([0] * input_dim)
+        rewards = [reward_init] * self.n_sensors
         dones = [False] * self.n_sensors
         for i, action in enumerate(actions):
             if self.remaining_energy[i] <= 0 or self.number_of_packets[i] <= 0:
@@ -381,7 +382,7 @@ 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)
 
-        rewards_energy = [reward_angle, reward_consumption_energy, reward_dispersion_remaining_energy, reward_number_of_packets]
+        rewards_energy = np.array([reward_angle, reward_consumption_energy, reward_dispersion_remaining_energy, reward_number_of_packets])
 
         #-- rewards related to the performance metrics
         reward_latency = self.compute_reward_latency()
@@ -389,10 +390,8 @@ class WSNRoutingEnv(gym.Env):
         reward_network_throughput = self.compute_reward_network_throughput()
         reward_packet_delivery_ratio = self.compute_reward_packet_delivery_ratio()
 
-        rewards_performance = [reward_latency, reward_network_throughput, 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 np.array([reward_consumption_energy, reward_dispersion_remaining_energy])
         return rewards_energy
     
 
@@ -488,7 +487,7 @@ class WSNRoutingEnv(gym.Env):
         d = len(rewards[0])
 
         # All sensors are represented by their raw rewards
-        query_vector = [max_reward] * d # Basically, the target is the base station
+        query_vector = np.array([max_reward] * d) # Basically, the target is the base station
 
         # Similarities between the query vector and the rewards
         similarities = [np.dot(query_vector, reward) for reward in rewards]

{gym_examples-3.0.728.dist-info → gym_examples-3.0.730.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.728
+Version: 3.0.730
 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-3.0.730.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=YZH_5LVBNsE51SZdDi3rZXTcfPU5Bpw1OBqSHx6rnGo,166
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=UiqeDmuDwZ96Qv91-eI8GzbTdpMeXlcbNqhVG5Ndt0U,26590
+gym_examples-3.0.730.dist-info/METADATA,sha256=5AKtgtPyq_6y3sWJjlym4zuqHbPMOCSNV6vhp0hsE-s,412
+gym_examples-3.0.730.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.730.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.730.dist-info/RECORD,,

gym_examples-3.0.728.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=_4a0uWUNYWJUbE3qDRnjR3v6dR59m-KEnWcp3-7CDes,166
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=x_SW_nOLr2k-EPFtkWu86GwLaMgZoizwx0ai6gUKydo,26679
-gym_examples-3.0.728.dist-info/METADATA,sha256=JzKg9Bkshk35opbb0gXkMyfQspFPsauZKzGlayJ2BSs,412
-gym_examples-3.0.728.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.728.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.728.dist-info/RECORD,,