Agilerl updates

.github/workflows/linux-tutorials-test.yml

@@ -17,7 +17,32 @@ jobs:
             fail-fast: false
             matrix:
                 python-version: ['3.8', '3.9', '3.10', '3.11']
-                tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/kaz, SB3/waterworld, SB3/connect_four, SB3/test, AgileRL]  # TODO: fix tutorials and add back Ray
+                tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/kaz, SB3/waterworld, SB3/connect_four, SB3/test]  # TODO: fix tutorials and add back Ray
+        steps:
+            - uses: actions/checkout@v4
+            - name: Set up Python ${{ matrix.python-version }}
+              uses: actions/setup-python@v4
+              with:
+                  python-version: ${{ matrix.python-version }}
+            - name: Install dependencies and run tutorials
+              run: |
+                  sudo apt-get install python3-opengl xvfb parallel
+                  export PATH=/path/to/parallel:$PATH
+                  export root_dir=$(pwd)
+                  cd tutorials/${{ matrix.tutorial }}
+                  pip install -r requirements.txt
+                  pip uninstall -y pettingzoo
+                  pip install -e $root_dir[testing]
+                  AutoROM -v
+                  for f in *.py; do xvfb-run -a -s "-screen 0 1024x768x24" python "$f"; done
+
+    agilerl-tutorial-test:
+        runs-on: ubuntu-latest
+        strategy:
+            fail-fast: false
+            matrix:
+                python-version: ['3.9', '3.10', '3.11']
+                tutorial: [AgileRL]
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

docs/tutorials/agilerl/DQN.md

@@ -612,10 +612,10 @@ Before we go any further in this tutorial, it would be helpful to define and set
    # Define the network configuration
    NET_CONFIG = {
       "arch": "cnn",  # Network architecture
-      "h_size": [64, 64],  # Actor hidden size
-      "c_size": [128],  # CNN channel size
-      "k_size": [4],  # CNN kernel size
-      "s_size": [1],  # CNN stride size
+      "hidden_size": [64, 64],  # Actor hidden size
+      "channel_size": [128],  # CNN channel size
+      "kernel_size": [4],  # CNN kernel size
+      "stride_size": [1],  # CNN stride size
       "normalize": False,  # Normalize image from range [0,255] to [0,1]
    }
 

tutorials/AgileRL/agilerl_dqn_curriculum.py

@@ -494,10 +494,10 @@ def outcome(self, action, player, return_length=False):
         # Define the network configuration
         NET_CONFIG = {
             "arch": "cnn",  # Network architecture
-            "h_size": [64, 64],  # Actor hidden size
-            "c_size": [128],  # CNN channel size
-            "k_size": [4],  # CNN kernel size
-            "s_size": [1],  # CNN stride size
+            "hidden_size": [64, 64],  # Actor hidden size
+            "channel_size": [128],  # CNN channel size
+            "kernel_size": [4],  # CNN kernel size
+            "stride_size": [1],  # CNN stride size
             "normalize": False,  # Normalize image from range [0,255] to [0,1]
         }
 

tutorials/AgileRL/agilerl_maddpg.py

@@ -22,10 +22,10 @@
     # Define the network configuration
     NET_CONFIG = {
         "arch": "cnn",  # Network architecture
-        "h_size": [32, 32],  # Network hidden size
-        "c_size": [32, 32],  # CNN channel size
-        "k_size": [3, 3],  # CNN kernel size
-        "s_size": [2, 2],  # CNN stride size
+        "hidden_size": [32, 32],  # Network hidden size
+        "channel_size": [32, 32],  # CNN channel size
+        "kernel_size": [3, 3],  # CNN kernel size
+        "stride_size": [2, 2],  # CNN stride size
         "normalize": True,  # Normalize image from range [0,255] to [0,1]
     }
 

tutorials/AgileRL/agilerl_matd3.py

@@ -21,7 +21,7 @@
     # Define the network configuration
     NET_CONFIG = {
         "arch": "mlp",  # Network architecture
-        "h_size": [32, 32],  # Actor hidden size
+        "hidden_size": [32, 32],  # Actor hidden size
     }
 
     # Define the initial hyperparameters

tutorials/AgileRL/requirements.txt

@@ -1,5 +1,4 @@
-agilerl==0.1.21; python_version >= '3.9'
-agilerl==0.1.20; python_version < '3.9'
+agilerl==0.1.22; python_version >= '3.9'
 pettingzoo[classic,atari,mpe]>=1.23.1
 SuperSuit>=3.9.0
 torch>=2.0.1