gym-examples 3.0.404__py3-none-any.whl → 3.0.406__py3-none-any.whl

gym_examples/__init__.py

@@ -5,4 +5,4 @@ register(
      entry_point="gym_examples.envs:WSNRoutingEnv",
 )
 
-__version__ = "3.0.404"
+__version__ = "3.0.406"

gym_examples/envs/wsn_env.py

@@ -54,21 +54,28 @@ max_reward = 1 # maximum reward value when the sensors sent data to the base sta
 # net = Attention(input_dim, output_dim)
 # net = net.double()  # Convert the weights to Double
 
+import torch
+import torch.nn as nn
+from gaussian_adaptive_attention import GaussianAdaptiveAttention  # Ensure this is properly imported
+
 class ScalarAttentionModel(nn.Module):
-    def __init__(self, input_dim):
+    def __init__(self, input_dim=4, output_dim=1):
         super(ScalarAttentionModel, self).__init__()
         # Initialize GaussianAdaptiveAttention
         self.ga_attention = GaussianAdaptiveAttention(
-            num_heads=1,  # Single head for simplicity
-            num_gaussians=4,  # Corresponds to your input length
-            attention_axis=0,  # Attention along the first axis
+            norm_axis=1,          # Normalize along feature axis
+            num_heads=1,          # Single head for simplicity
+            num_gaussians=input_dim,  # Match input length
+            padding_value=None,   # Change if padding exists
         )
-        self.output_layer = nn.Linear(input_dim, 1)  # Map to scalar output
+        self.output_layer = nn.Linear(input_dim, output_dim)  # Map to scalar output
 
     def forward(self, x):
+        # Ensure input is 2D
+        if x.dim() == 1:
+            x = x.unsqueeze(0)  # Add batch dimension if necessary
         # Apply GaussianAdaptiveAttention
-        attention_output = self.ga_attention(x.unsqueeze(0))  # Add batch dim
-        attention_output = attention_output.squeeze(0)  # Remove batch dim
+        attention_output = self.ga_attention(x)
         # Map to scalar
         scalar_output = self.output_layer(attention_output)
         return scalar_output

{gym_examples-3.0.404.dist-info → gym_examples-3.0.406.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gym-examples
-Version: 3.0.404
+Version: 3.0.406
 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-3.0.406.dist-info/RECORD

@@ -0,0 +1,7 @@
+gym_examples/__init__.py,sha256=93ZP0az3WubSxQddsv4ZBMSOcGLaybt50oMK3bVh0Ls,166
+gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
+gym_examples/envs/wsn_env.py,sha256=pJVSjoGOfXumb5E_74ArsFywoh4BqGlV5azKU3qAbIw,27591
+gym_examples-3.0.406.dist-info/METADATA,sha256=ZN3X9fGxl0OwSzdtDLcSucYFzOUKUEXKnk3lb1-K_II,412
+gym_examples-3.0.406.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+gym_examples-3.0.406.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
+gym_examples-3.0.406.dist-info/RECORD,,

gym_examples-3.0.404.dist-info/RECORD

@@ -1,7 +0,0 @@
-gym_examples/__init__.py,sha256=kSSUOydEpYd6p-FwjBNXhpeRAH5NAZ7lXf2MEHD66RE,166
-gym_examples/envs/__init__.py,sha256=lgMe4pyOuUTgTBUddM0iwMlETsYTwFShny6ifm8PGM8,53
-gym_examples/envs/wsn_env.py,sha256=hLM8UtyVrLn-dm_8ZazOjR_iuBk9mLxzCwRRsIbopWs,27341
-gym_examples-3.0.404.dist-info/METADATA,sha256=vrZnbnEa5pzhM2LTWiayHm5fMGebm-KKeVxMyBG_yuE,412
-gym_examples-3.0.404.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-gym_examples-3.0.404.dist-info/top_level.txt,sha256=rJRksoAF32M6lTLBEwYzRdo4PgtejceaNnnZ3HeY_Rk,13
-gym_examples-3.0.404.dist-info/RECORD,,