gym-examples 3.0.21__py3-none-any.whl → 3.0.23__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (7) hide show
  1. gym_examples/__init__.py +1 -1
  2. gym_examples/envs/wsn_env.py +5 -4
  3. {gym_examples-3.0.21.dist-info → gym_examples-3.0.23.dist-info}/METADATA +1 -1
  4. gym_examples-3.0.23.dist-info/RECORD +7 -0
  5. gym_examples-3.0.21.dist-info/RECORD +0 -7
  6. {gym_examples-3.0.21.dist-info → gym_examples-3.0.23.dist-info}/WHEEL +0 -0
  7. {gym_examples-3.0.21.dist-info → gym_examples-3.0.23.dist-info}/top_level.txt +0 -0
gym_examples/__init__.py CHANGED
@@ -6,4 +6,4 @@ register(
6
6
  max_episode_steps=50,
7
7
  )
8
8
 
9
- __version__ = "3.0.21"
9
+ __version__ = "3.0.23"
gym_examples/envs/wsn_env.py CHANGED
@@ -137,7 +137,8 @@ class WSNRoutingEnv(gym.Env):
137
137
  self.total_latency += self.packet_latency[i] + latency_per_hop
138
138
  self.packet_latency[i] = 0
139
139
 
140
- rewards[i] = self.compute_individual_rewards(i, action)
140
+ # rewards[i] = self.compute_individual_rewards(i, action)
141
+ rewards[i] = np.ones(input_dim) # input_dim should be equal to the number of individual rewards
141
142
  dones[i] = True
142
143
  else:
143
144
  distance = np.linalg.norm(self.sensor_positions[i] - self.sensor_positions[action])
@@ -164,9 +165,9 @@ class WSNRoutingEnv(gym.Env):
164
165
  self.number_of_packets[action] += self.number_of_packets[i]
165
166
  self.number_of_packets[i] = 0 # Reset the number of packets of the sensor i
166
167
  # Calculate final reward
167
- rewards_individual = torch.tensor(rewards[i], dtype=torch.double)
168
- final_reward = net(rewards_individual)
169
- # final_reward = np.sum(rewards[i])
168
+ # rewards_individual = torch.tensor(rewards[i], dtype=torch.double)
169
+ # final_reward = net(rewards_individual)
170
+ final_reward = np.sum(rewards[i])
170
171
  # weights = np.ones(self.n_sensors, dtype=int)
171
172
  # final_reward = np.sum(reward * weight for reward, weight in zip(rewards[i], weights))
172
173
  rewards[i] = final_reward
{gym_examples-3.0.21.dist-info → gym_examples-3.0.23.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: gym-examples
3
- Version: 3.0.21
3
+ Version: 3.0.23
4
4
  Summary: A custom environment for multi-agent reinforcement learning focused on WSN routing.
5
5
  Home-page: https://github.com/gedji/CODES.git
6
6
  Author: Georges Djimefo
gym_examples-3.0.23.dist-info/RECORD ADDED
@@ -0,0 +1,7 @@
1
+ gym_examples/__init__.py,sha256=6UlH1lVgV39cBe9M6fWfhp8pHDJA65h2z8e7m6cQxxI,193
2
+ gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
3
+ gym_examples/envs/wsn_env.py,sha256=FOnvswLo3G33xNfip4zNNzMKjYs5m_lJLOvhqhR6yPo,18737
4
+ gym_examples-3.0.23.dist-info/METADATA,sha256=Jkko_DEMGrG2u2jUwZU4X_OD_qrc2Z8WBE_deTLD3EE,411
5
+ gym_examples-3.0.23.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
6
+ gym_examples-3.0.23.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
7
+ gym_examples-3.0.23.dist-info/RECORD,,
gym_examples-3.0.21.dist-info/RECORD DELETED
@@ -1,7 +0,0 @@
1
- gym_examples/__init__.py,sha256=MzRHchFiM8e4DrlFV57GNAYTp3kn04KrDjL43lJM_2E,193
2
- gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
3
- gym_examples/envs/wsn_env.py,sha256=E0kWXS2yQqB0DDl1n5www2auLsjw0HLo-J_sL3nA4zY,18620
4
- gym_examples-3.0.21.dist-info/METADATA,sha256=JIuPx6HulQ3n_gYcvPd6Nol0_d1Jj_6-hEJJKYYpbgw,411
5
- gym_examples-3.0.21.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
6
- gym_examples-3.0.21.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
7
- gym_examples-3.0.21.dist-info/RECORD,,