gym-examples 3.0.134__py3-none-any.whl → 3.0.136__py3-none-any.whl

gym_examples/__init__.py

@@ -6,4 +6,4 @@ register(
      max_episode_steps=50,
 )
 
-__version__ = "3.0.134"
+__version__ = "3.0.136"

gym_examples/envs/wsn_env.py

@@ -63,12 +63,14 @@ class WSNRoutingEnv(gym.Env):
         #     tuple([self._get_observation_space() for _ in range(self.n_sensors)])
         # )
 
-        self.observation_space = gym.spaces.Dict({
-            'remaining_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(len(self.remaining_energy),), dtype=np.float32),
-            'consumption_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(len(self.remaining_energy),), dtype=np.float32),
-            'sensor_positions': gym.spaces.Box(low=lower_bound, high=upper_bound, shape=(len(self.sensor_positions), 2), dtype=np.float32),
-            'number_of_packets': gym.spaces.Box(low=0, high=self.n_sensors * initial_number_of_packets + 1, shape=(len(self.number_of_packets),), dtype=int)
-        })
+        # self.observation_space = gym.spaces.Dict({
+        #     'remaining_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(self.n_agents,), dtype=np.float32),
+        #     'consumption_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(self.n_agents,), dtype=np.float32),
+        #     'sensor_positions': gym.spaces.Box(low=lower_bound, high=upper_bound, shape=(self.n_agents, 2), dtype=np.float32),
+        #     'number_of_packets': gym.spaces.Box(low=0, high=self.n_sensors * initial_number_of_packets + 1, shape=(self.n_agents,), dtype=int)
+        # })
+
+        self.observation_space = self._get_observation_space()
 
         # self.action_space = Tuple(tuple([Discrete(self.n_sensors + 1)] * self.n_agents))
         self.action_space = gym.spaces.MultiDiscrete([self.n_sensors + 1] * self.n_agents)
@@ -204,13 +206,21 @@ class WSNRoutingEnv(gym.Env):
             'number_of_packets': np.array(self.number_of_packets)
         }
 
+    # def _get_observation_space(self):
+    #     return gym.spaces.Dict({
+    #         'remaining_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(len(self.remaining_energy),), dtype=np.float32),
+    #         'consumption_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(len(self.remaining_energy),), dtype=np.float32),
+    #         'sensor_positions': gym.spaces.Box(low=lower_bound, high=upper_bound, shape=(len(self.sensor_positions), 2), dtype=np.float32),
+    #         'number_of_packets': gym.spaces.Box(low=0, high=self.n_sensors * initial_number_of_packets + 1, shape=(len(self.number_of_packets),), dtype=int)
+    #     })
+
     def _get_observation_space(self):
         return gym.spaces.Dict({
-            'remaining_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(len(self.remaining_energy),), dtype=np.float32),
-            'consumption_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(len(self.remaining_energy),), dtype=np.float32),
-            'sensor_positions': gym.spaces.Box(low=lower_bound, high=upper_bound, shape=(len(self.sensor_positions), 2), dtype=np.float32),
-            'number_of_packets': gym.spaces.Box(low=0, high=self.n_sensors * initial_number_of_packets + 1, shape=(len(self.number_of_packets),), dtype=int)
-        })
+                'remaining_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(self.n_agents,), dtype=np.float32),
+                'consumption_energy': gym.spaces.Box(low=0, high=initial_energy, shape=(self.n_agents,), dtype=np.float32),
+                'sensor_positions': gym.spaces.Box(low=lower_bound, high=upper_bound, shape=(self.n_agents, 2), dtype=np.float32),
+                'number_of_packets': gym.spaces.Box(low=0, high=self.n_sensors * initial_number_of_packets + 1, shape=(self.n_agents,), dtype=int)
+            })
 
 
     def get_state(self):

{gym_examples-3.0.134.dist-info → gym_examples-3.0.136.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.134
+Version: 3.0.136
 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-3.0.136.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=xvHRv3fRlCpsfAE5OWZyelEhTTW1ttWxeyhdR2wnYzI,194
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=h9SNs1zmilOorshyy9oK80xC4dwib8uC_UVhNoN_6XE,23947
+gym_examples-3.0.136.dist-info/METADATA,sha256=xqB0l3vTR9XjCEnHm4dX_gxBnVaK7nD1ozEz6kNjMpc,412
+gym_examples-3.0.136.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.136.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.136.dist-info/RECORD,,

gym_examples-3.0.134.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=NDW_AoYQPwLsSSYhRWfejgVCkMyXx98eNpLQEYLe4-8,194
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=dwIYGkIGyeuhF2jmq4WoOGcgzN2ytfAqrU-WPIIxoOI,23289
-gym_examples-3.0.134.dist-info/METADATA,sha256=ZBMLM_U-MRZze2R6hKGKYG9kcoO5sdoYd2a15ytT-68,412
-gym_examples-3.0.134.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.134.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.134.dist-info/RECORD,,