gym-examples 3.0.662__py3-none-any.whl → 3.0.664__py3-none-any.whl

gym_examples/__init__.py

@@ -5,4 +5,4 @@ register(
      entry_point="gym_examples.envs:WSNRoutingEnv",
 )
 
-__version__ = "3.0.662"
+__version__ = "3.0.664"

gym_examples/envs/wsn_env.py

@@ -58,8 +58,9 @@ class WSNRoutingEnv(gym.Env):
 
     ALGO_NAME = "" # Global flag to control the algorithm name
     gym_examples_current_version = "" # Global flag to control the gym_examples version
+    coefficients = [] # Global flag for the weights of all the agents
 
-    def __init__(self, n_sensors = 90, coverage_radius=(upper_bound - lower_bound) * 3/20, num_timesteps = None, version = None):
+    def __init__(self, n_sensors = 30, coverage_radius=(upper_bound - lower_bound) * 3/20, num_timesteps = None, version = None):
 
         super(WSNRoutingEnv, self).__init__()
         # Create filenames to save statistics for evaluation
@@ -97,6 +98,8 @@ class WSNRoutingEnv(gym.Env):
         self.reset()        
 
     def reset(self):
+        print("\n============================================")
+        print(f"Episode count: {self.episode_count}")
         if self.number_of_steps > 30000: # Change 30000 to a parameter taken from args or kwargs
             self.episode_returns.append(self.episode_return)
             observations = self._get_obs()
@@ -140,6 +143,9 @@ class WSNRoutingEnv(gym.Env):
 
         self.get_metrics()
 
+        if self.episode_count > 1:
+            print(f"Episode return: {self.episode_return}")
+
         return self._get_obs()
 
 
@@ -231,6 +237,7 @@ class WSNRoutingEnv(gym.Env):
         dones = bool(np.all(dones))
 
         self.episode_return += rewards
+
         return self._get_obs(), rewards, dones, self.get_metrics()
 
 
@@ -258,6 +265,20 @@ class WSNRoutingEnv(gym.Env):
     def get_avail_actions(self):
         return [list(range(self.n_sensors + 1)) for _ in range(self.n_sensors)]
     
+    def build_weigths_agents(self, coefficients):
+        '''
+        We would like to compute the similarity score between the agents and the base station:
+        For this, we consider that each agent is represented by a vector constituted of:
+        - number of packets after the action
+        - remaining energy after the action
+        - distance to the base station
+        The vector of the base station is constituted of:
+        - number of packets after the action: all the times, we consider is equal to 0
+        - remaining energy after the action: all the times, we consider is equal to initial_energy
+        - distance to the base station: all the times, we consider is equal to 0 
+        '''
+        vector_referee = [0, 0, 1] # Vector of the base station
+
 
     def update_sensor_energies(self, i, delta_energy):
         self.remaining_energy[i] -= delta_energy

{gym_examples-3.0.662.dist-info → gym_examples-3.0.664.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.662
+Version: 3.0.664
 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-3.0.664.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=nf1oj2PGof0ZMExWKFk05GXrJ4fwkgUTbCkIKEv3nr8,166
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=tc7KB1SIzx-7Ee1kd3Qttf1LhmvBy5GdqZTa1MFldaI,26363
+gym_examples-3.0.664.dist-info/METADATA,sha256=H_DM3iYfLc7732DNu4rfn_h-keZQ_IXycxctRHh9pHM,412
+gym_examples-3.0.664.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.664.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.664.dist-info/RECORD,,

gym_examples-3.0.662.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=C4ZusYlaub4xCgqI-7ThaSoyGMMSTO1oJxBIyMCyTMw,166
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=CELBjrF9LYLOItWv7jr8CoUyH8nWRvrFwxzfVl96Tbs,25280
-gym_examples-3.0.662.dist-info/METADATA,sha256=VRNcl8g9c_I3hj0-i3QbjSCUQYtmYDzH8m02HrrFxqA,412
-gym_examples-3.0.662.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.662.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.662.dist-info/RECORD,,