Merge pull request #194 from huangshiyu13/main

fix leaky_relu twice written
OpenRL-Lab · Aug 11, 2023 · ad925cc · ad925cc
2 parents 5c78ecf + 1ef8a18
commit ad925cc
Show file tree

Hide file tree

Showing 5 changed files with 9 additions and 9 deletions.
diff --git a/openrl/configs/config.py b/openrl/configs/config.py
@@ -480,7 +480,7 @@ def create_config_parser():
         "--activation_id",
         type=int,
         default=1,
-        help="choose 0 to use tanh, 1 to use relu, 2 to use leaky relu, 3 to use elu",
+        help="choose 0 to use tanh, 1 to use relu, 2 to use leaky relu, 3 to use selu",
     )
     parser.add_argument(
         "--use_popart",

diff --git a/openrl/modules/networks/utils/attention.py b/openrl/modules/networks/utils/attention.py
@@ -80,7 +80,7 @@ def __init__(
         active_func = [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):
@@ -194,7 +194,7 @@ def __init__(self, split_shape, d_model, use_orthogonal=True, activation_id=1):
         active_func = [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):
@@ -252,7 +252,7 @@ def __init__(self, split_shape, d_model, use_orthogonal=True, activation_id=1):
         active_func = [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):

diff --git a/openrl/modules/networks/utils/cnn.py b/openrl/modules/networks/utils/cnn.py
@@ -23,7 +23,7 @@ def __init__(
         [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):

diff --git a/openrl/modules/networks/utils/mix.py b/openrl/modules/networks/utils/mix.py
@@ -97,7 +97,7 @@ def _convert(params):
         active_func = [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):
@@ -189,7 +189,7 @@ def _build_mlp_model(self, obs_shape, hidden_size, use_orthogonal, activation_id
         active_func = [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):

diff --git a/openrl/modules/networks/utils/mlp.py b/openrl/modules/networks/utils/mlp.py
@@ -13,7 +13,7 @@ def __init__(self, input_dim, hidden_size, layer_N, use_orthogonal, activation_i
         active_func = [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):
@@ -53,7 +53,7 @@ def __init__(self, input_dim, hidden_size, use_orthogonal, activation_id):
         active_func = [nn.Tanh(), nn.ReLU(), nn.LeakyReLU(), nn.ELU()][activation_id]
         init_method = [nn.init.xavier_uniform_, nn.init.orthogonal_][use_orthogonal]
         gain = nn.init.calculate_gain(
-            ["tanh", "relu", "leaky_relu", "leaky_relu"][activation_id]
+            ["tanh", "relu", "leaky_relu", "selu"][activation_id]
         )
 
         def init_(m):