gym-examples 3.0.261__py3-none-any.whl → 3.0.263__py3-none-any.whl

gym_examples/__init__.py

@@ -5,4 +5,4 @@ register(
      entry_point="gym_examples.envs:WSNRoutingEnv",
 )
 
-__version__ = "3.0.261"
+__version__ = "3.0.263"

gym_examples/envs/wsn_env.py

@@ -82,7 +82,8 @@ 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 = MultiDiscrete([self.n_agents, self.n_sensors + 1]) 
+        self.action_space = Discrete(self.n_agents * (self.n_sensors + 1))
 
         self.reset()        
 
@@ -130,7 +131,6 @@ class WSNRoutingEnv(gym.Env):
 
 
     def step(self, actions):
-        print(f"Actions in step of WSNRoutingEnv: {actions} and type {type(actions)}")
         self.steps += 1 
         # rewards = [-max_reward] * self.n_sensors
         reward = -max_reward
@@ -138,7 +138,9 @@ class WSNRoutingEnv(gym.Env):
         done = False
         # actions = [actions[i] for i in range(self.n_agents)] # We want to go back from the MultiDiscrete action space to a tuple of tuple of Discrete action spaces
         # for i, action in enumerate(actions):
-        for i, action in [actions]: # This loop is for the PPO algorithm: actions is a numpy array of shape (1, 2)
+        selected_sensor = actions // (self.n_sensors + 1)
+        target = actions % (self.n_sensors + 1)
+        for i, action in [np.array([selected_sensor, target])]: # This loop is for the PPO algorithm: actions is a numpy array of shape (1, 2)
             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
             

{gym_examples-3.0.261.dist-info → gym_examples-3.0.263.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.261
+Version: 3.0.263
 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-3.0.263.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=V-lDBqJirIbwK5vx8WNT5JyIwiwk22PGBiYSvm6JPo8,166
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=Ee3PTxhwKw2igwK5z465IdgK3mP0ParioXCni6BqXiE,26695
+gym_examples-3.0.263.dist-info/METADATA,sha256=rpRe1k5FCesyS6hKApj_Z-_sQAjJ01WM90Mzk_a5XPs,412
+gym_examples-3.0.263.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.263.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.263.dist-info/RECORD,,

gym_examples-3.0.261.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=EYmnHn1aYn3x_bUd8fgo7-mIabHA6MlIYIECdK0RgLo,166
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=2ldLj0D1jkHY93C4m0bfZpRZXxMJN79um7lfDIF_9l8,26569
-gym_examples-3.0.261.dist-info/METADATA,sha256=hB4fNZreReHqZS9sULIyJYEsPyclC0Afdu6zHI7P5Bk,412
-gym_examples-3.0.261.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.261.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.261.dist-info/RECORD,,