gym-examples 3.0.285__py3-none-any.whl → 3.0.287__py3-none-any.whl

gym_examples/__init__.py

@@ -5,4 +5,4 @@ register(
      entry_point="gym_examples.envs:WSNRoutingEnv",
 )
 
-__version__ = "3.0.285"
+__version__ = "3.0.287"

gym_examples/envs/wsn_env.py

@@ -81,10 +81,7 @@ class WSNRoutingEnv(gym.Env):
         )
 
         # self.action_space = Tuple(tuple([Discrete(self.n_sensors + 1)] * self.n_agents))
-        # self.action_space = MultiDiscrete([self.n_sensors + 1] * self.n_agents)
-        # self.action_space = MultiDiscrete([self.n_agents, self.n_sensors + 1]) 
-        # self.action_space = Discrete(self.n_sensors + 1)  # +1 for the base station
-        self.action_space = Discrete((self.n_sensors + 1)**self.n_agents)
+        self.action_space = MultiDiscrete([self.n_sensors + 1] * self.n_agents)
 
         self.reset()        
 
@@ -120,7 +117,6 @@ class WSNRoutingEnv(gym.Env):
         self.steps += 1 
         rewards = [-max_reward] * self.n_sensors
         dones = [False] * self.n_sensors
-        actions = self.to_base_n(actions, self.n_sensors + 1)
         for i, action in enumerate(actions):
             if self.remaining_energy[i] <= 0 or self.number_of_packets[i] <= 0:
                 continue  # Skip if sensor has no energy left or no packets to transmit
@@ -195,11 +191,12 @@ class WSNRoutingEnv(gym.Env):
 
         rewards = [reward.item() if isinstance(reward, torch.Tensor) else reward for reward in rewards] # Convert the reward to a float
         rewards = np.mean(rewards) # Average the rewards
-        
+
         for i in range(self.n_sensors):
             if not dones[i]:
                 dones[i] = self.remaining_energy[i] <= 0 or self.number_of_packets[i] == 0
         dones = np.all(dones)
+        print(f"done: {dones}, and type: {type(dones)}")
 
         return self._get_obs(), rewards, dones, self.get_metrics()
 

{gym_examples-3.0.285.dist-info → gym_examples-3.0.287.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.285
+Version: 3.0.287
 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-3.0.287.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=_zsZY7FYGbXB0Ei4w6ldnJhp56xvi7MFMIUqsPtm_ZA,166
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=Mv_1wuAt-ancx-BfkCCVXjBssaENSliEU8jgypys_2c,23350
+gym_examples-3.0.287.dist-info/METADATA,sha256=283fW25USJEPBYXfleS0cRs0F7bFial5AjjSzdYC05M,412
+gym_examples-3.0.287.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.287.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.287.dist-info/RECORD,,

gym_examples-3.0.285.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=RG4x72mbBXJgNSIrzig4Fq6xeAVsPtwrVaN8fHLoVHc,166
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=7AKFR_Q4I_GADV3Q78g-JYacUSIwRDzjxLRZ5X9lzFc,23610
-gym_examples-3.0.285.dist-info/METADATA,sha256=fR_FUKKdoAUxYEjQ8KbeVC4quinNkfxfqShtSaWFMlo,412
-gym_examples-3.0.285.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.285.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.285.dist-info/RECORD,,