Implement Gymnasium-compliant PPO script

.github/workflows/tests.yaml

@@ -134,7 +134,7 @@ jobs:
         run: poetry run pytest tests/test_procgen.py
 
 
-  test-mujoco-envs:
+  test-mujoco_py-envs:
     strategy:
       fail-fast: false
       matrix:
@@ -152,26 +152,26 @@ jobs:
         with:
           poetry-version: ${{ matrix.poetry-version }}
 
-      # mujoco tests
+      # mujoco_py tests
       - name: Install core dependencies
         run: poetry install --with pytest
       - name: Install pybullet dependencies
         run: poetry install --with pybullet
-      - name: Install mujoco dependencies
-        run: poetry install --with mujoco
+      - name: Install mujoco_py dependencies
+        run: poetry install --with mujoco_py
       - name: Install jax dependencies
         run: poetry install --with jax
       - name: Downgrade setuptools
         run: poetry run pip install setuptools==59.5.0
-      - name: install mujoco dependencies
+      - name: install mujoco_py dependencies
         run: |
           sudo apt-get update && sudo apt-get -y install wget unzip software-properties-common \
             libgl1-mesa-dev \
             libgl1-mesa-glx \
             libglew-dev \
             libosmesa6-dev patchelf
-      - name: Run mujoco tests
-        run: poetry run pytest tests/test_mujoco.py
+      - name: Run mujoco_py tests
+        run: poetry run pytest tests/test_mujoco_py.py
 
   test-envpool-envs:
     strategy: