Adding Gymnasium Compatibility

.github/workflows/python-app.yml

@@ -114,5 +114,9 @@ jobs:
     - name: Run Test jupyter-notebooks tutorials
       if: ${{ runner.os == 'Linux' }}
       run: |
-        conda activate $CONDA_DEFAULT_ENV
-        source myosuite/tests/test_tutorials.sh
+        source myosuite/tests/test_tutorials.sh
+
+    - name: Run Test gym/gymnasium + stable-baselines3
+      if: ${{ runner.os == 'Linux' }}
+      run: |
+        source myosuite/tests/test_versions.sh

README.md

@@ -59,8 +59,7 @@ It is possible to create and interface with MyoSuite environments just like any
 
 
 ```python
-import myosuite
-import gym
+from myosuite.utils import gym
 env = gym.make('myoElbowPose1D6MRandom-v0')
 env.reset()
 for _ in range(1000):

docs/source/install.rst

@@ -60,8 +60,7 @@ For example, to use the ``myoElbowPose1D6MRandom-v0`` environment it is possible
 
 .. code-block:: python
 
-   import myosuite
-   import gym
+   from myosuite.utils import gym
    env = gym.make('myoElbowPose1D6MRandom-v0')
    env.reset()
    for _ in range(1000):

docs/source/tutorials.rst

@@ -25,8 +25,7 @@ Example on how to use an environment e.g. send random movements
 
 .. code-block:: python
 
-    import myosuite
-    import gym
+    from myosuite.utils import gym
     env = gym.make('myoElbowPose1D6MRandom-v0')
     env.reset()
     for _ in range(1000):
@@ -43,8 +42,7 @@ Example on how to generate and visualize a movement e.g. index flexion, and visu
 
 .. code-block:: python
 
-    import myosuite
-    import gym
+    from myosuite.utils import gym
     env = gym.make('myoHandPoseRandom-v0')
     env.reset()
     for _ in range(1000):
@@ -60,8 +58,7 @@ Example on using a policy e.g. elbow flexion, and change non-stationaries
 
 .. code-block:: python
 
-    import myosuite
-    import gym
+    from myosuite.utils import gym
     policy = "iterations/best_policy.pickle"
 
     import pickle
@@ -83,8 +80,7 @@ This example shows how to add fatigue to a model. It tests random actions on a m
 
 .. code-block:: python
 
-    import myosuite
-    import gym
+    from myosuite.utils import gym
     env = gym.make('myoElbowPose1D6MRandom-v0')
     env.reset()
     for _ in range(1000):
@@ -108,8 +104,7 @@ This example shows how to add sarcopenia or muscle weakness to a model. It tests
 
 .. code-block:: python
 
-    import myosuite
-    import gym
+    from myosuite.utils import gym
     env = gym.make('myoElbowPose1D6MRandom-v0')
     env.reset()
     for _ in range(1000):
@@ -134,8 +129,7 @@ This example shows how load a model with physical tendon transfer.
 
 .. code-block:: python
 
-    import myosuite
-    import gym
+    from myosuite.utils import gym
     env = gym.make('myoHandKeyTurnFixed-v0')
     env.reset()
     for _ in range(1000):
@@ -171,8 +165,7 @@ If you want to load and execute the pre-trained DEP-RL baseline. Make sure that
 
 .. code-block:: python
 
-    import gym
-    import myosuite
+    from myosuite.utils import gym
     import deprl
 
     # we can pass arguments to the environments here

docs/source/tutorials/1_Get_Started.ipynb

@@ -22,8 +22,7 @@
     }
    ],
    "source": [
-    "import myosuite\n",
-    "import gym\n",
+    "from myosuite.utils import gym\n",
     "import skvideo.io\n",
     "import numpy as np\n",
     "import os"

docs/source/tutorials/2_Load_policy.ipynb

@@ -6,8 +6,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import myosuite\n",
-    "import gym\n",
+    "from myosuite.utils import gym\n",
     "import skvideo.io\n",
     "import numpy as np\n",
     "import os"
@@ -79,7 +78,7 @@
     "        frames.append(frame)\n",
     "        o = env.get_obs()\n",
     "        a = pi.get_action(o)[0]\n",
-    "        next_o, r, done, ifo = env.step(a) # take an action based on the current observation\n",
+    "        next_o, r, done, *_, ifo = env.step(a) # take an action based on the current observation\n",
     "env.close()\n",
     "\n",
     "os.makedirs('videos', exist_ok=True)\n",

docs/source/tutorials/3_Analyse_movements.ipynb

@@ -6,8 +6,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import myosuite\n",
-    "import gym\n",
+    "from myosuite.utils import gym\n",
     "import skvideo.io\n",
     "import numpy as np\n",
     "import os"
@@ -45,7 +44,7 @@
     "    for _ in range(100): # 100 samples for each episode\n",
     "        o = env.get_obs()\n",
     "        a = pi.predict(o)[0]\n",
-    "        next_o, r, done, ifo = env.step(a) # take a random action\n",
+    "        next_o, r, done, *_, ifo = env.step(a) # take a random action\n",
     "                    \n",
     "        data_store.append({\"action\":a.copy(), \n",
     "                            \"jpos\":env.sim.data.qpos.copy(), \n",

docs/source/tutorials/4_Train_policy.ipynb

@@ -6,8 +6,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import myosuite\n",
-    "import gym\n",
+    "from myosuite.utils import gym\n",
     "import skvideo.io\n",
     "import numpy as np\n",
     "import os"
@@ -122,7 +121,7 @@
     "        frames.append(frame[::-1,:,:])\n",
     "        o = env.get_obs()\n",
     "        a = pi.get_action(o)[0]\n",
-    "        next_o, r, done, ifo = env.step(a) # take an action based on the current observation\n",
+    "        next_o, r, done, *_, ifo = env.step(a) # take an action based on the current observation\n",
     "env.close()\n",
     "\n",
     "os.makedirs('videos', exist_ok=True)\n",

docs/source/tutorials/4a_deprl.ipynb

@@ -29,10 +29,8 @@
     }
    ],
    "source": [
-    "\n",
-    "import gym, myosuite\n",
-    "import deprl\n",
-    "import gym"
+    "from myosuite.utils import gym\n",
+    "import deprl"
    ]
   },
   {
@@ -75,10 +73,10 @@
    "source": [
     "policy = deprl.load_baseline(env)\n",
     "\n",
-    "obs = env.reset()\n",
+    "obs = env.reset()[0]\n",
     "for _ in range(T):\n",
     "    action = policy(obs)\n",
-    "    obs, rew, done, info = env.step(action)\n",
+    "    obs, rew, done, *_, info = env.step(action)\n",
     "    if done:\n",
     "        break\n",
     "env.close()\n",
@@ -95,13 +93,6 @@
    "source": [
     "If you want to load your own policy, replace `deprl.load_baseline(env)` with `deprl.load(path, env)`. This will automatically load it for you. We also provide more advanced commands like `python -m deprl.play --path /folder/` to setup a visualization script."
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

docs/source/tutorials/4c_Train_SB_policy.ipynb

@@ -6,8 +6,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import myosuite\n",
-    "import gym\n",
+    "from myosuite.utils import gym\n",
     "import skvideo.io\n",
     "import numpy as np\n",
     "import os"
@@ -92,7 +91,7 @@
     "        frames.append(frame[::-1,:,:])\n",
     "        o = env.get_obs()\n",
     "        a = pi.predict(o)[0]\n",
-    "        next_o, r, done, ifo = env.step(a) # take an action based on the current observation\n",
+    "        next_o, r, done, *_, ifo = env.step(a) # take an action based on the current observation\n",
     "env.close()\n",
     "\n",
     "os.makedirs('videos', exist_ok=True)\n",

docs/source/tutorials/5_Move_Hand_Fingers.ipynb

@@ -6,8 +6,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import myosuite\n",
-    "import gym\n",
+    "from myosuite.utils import gym\n",
     "import skvideo.io\n",
     "import numpy as np\n",
     "import os"

docs/source/tutorials/SAR/SAR tutorial.ipynb → docs/source/tutorials/SAR/SAR_tutorial.ipynb

@@ -50,16 +50,15 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "8526f610",
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# !pip install stable-baselines3==1.7.0\n",
     "# !pip install joblib\n",
     "# !pip install scikit-learn\n",
     "# !pip install tqdm\n",
-    "# !pip install matplotlib"
+    "# !pip install matplotlib\n",
+    "# !pip install gymnasium"
    ]
   },
   {
@@ -220,7 +219,7 @@
     "                o = env.get_obs()\n",
     "                o = vec.normalize_obs(o)\n",
     "                a, __ = model.predict(o, deterministic=False)\n",
-    "                next_o, r, done, info = env.step(a)\n",
+    "                next_o, r, done, *_, info = env.step(a)\n",
     "                rewards += r\n",
     "            preview_rewards.append(rewards)\n",
     "        reward_threshold = np.percentile(preview_rewards, percentile)\n",
@@ -236,14 +235,14 @@
     "                o = env.get_obs()\n",
     "                o = vec.normalize_obs(o)\n",
     "                a, __ = model.predict(o, deterministic=False)\n",
-    "                next_o, r, done, info = env.step(a)\n",
+    "                next_o, r, done, *_, info = env.step(a)\n",
     "                acts.append(env.sim.data.act.copy())\n",
     "                rewards += r\n",
     "\n",
     "            if rewards > reward_threshold:\n",
     "                solved_acts.extend(acts)\n",
     "\n",
-    "    return solved_acts"
+    "    return np.array(solved_acts)"
    ]
   },
   {
@@ -562,6 +561,16 @@
     "muscle_data = get_activations(name='play_period', env_name='myoLegWalk-v0', seed='0', episodes=1000)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39ee90ed-73c9-4b02-ba56-488d539c4993",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "muscle_data.shape"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -650,6 +659,16 @@
     "show_video(f\"{video_name}.mp4\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88c68a0a-eede-4505-b800-5c0ccdd831bc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gym.make(f'myoLeg{new_terrain}TerrainWalk-v0')"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "9d10cb1e",
@@ -976,7 +995,8 @@
     "        if syn_nosyn:\n",
     "            env = SynNoSynWrapper(gym.make(test_env_name), ica, pca, normalizer, phi)\n",
     "        else:\n",
-    "            env = SynergyWrapper(gym.make(test_env_name), ica, pca, normalizer, phi)\n",
+    "            # env = SynergyWrapper(gym.make(test_env_name), ica, pca, normalizer, phi)\n",
+    "            env = SynergyWrapper(gym.make(test_env_name), ica, pca, normalizer)\n",
     "    else:\n",
     "        env = gym.make(test_env_name)\n",
     "    env.reset()\n",
@@ -992,7 +1012,7 @@
     "            o = env.get_obs()\n",
     "            o = vec.normalize_obs(o)\n",
     "            a, __ = model.predict(o, deterministic=determ)\n",
-    "            next_o, r, done, info = env.step(a)\n",
+    "            next_o, r, done, *_, info = env.step(a)\n",
     "            is_solved.append(info['solved'])\n",
     "        \n",
     "        if sum(is_solved) > 0:\n",
@@ -1085,7 +1105,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.9.18"
   }
  },
  "nbformat": 4,

docs/source/tutorials/SAR/SAR_tutorial_utils.py

@@ -1,5 +1,4 @@
-import myosuite
-import gym
+from myosuite.utils import gym
 
 from stable_baselines3 import SAC, PPO
 from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
@@ -347,7 +346,8 @@ def get_vid(name, env_name, seed, episodes, video_name, determ=False,
         if syn_nosyn:
             env = SynNoSynWrapper(gym.make(env_name), ica, pca, normalizer, phi)
         else:
-            env = SynergyWrapper(gym.make(env_name), ica, pca, normalizer, phi)
+            # env = SynergyWrapper(gym.make(env_name), ica, pca, normalizer, phi)
+            env = SynergyWrapper(gym.make(env_name), ica, pca, normalizer)
     else:
         env = gym.make(env_name)
 
@@ -372,7 +372,7 @@ def get_vid(name, env_name, seed, episodes, video_name, determ=False,
             frame = env.sim.renderer.render_offscreen(width=640, height=480,camera_id=camera)
             frames.append(frame)
 
-            next_o, r, done, info = env.step(a)
+            next_o, r, done,  *_, info = env.step(a)
             is_solved.append(info['solved'])
 
             rs+=r

docs/source/tutorials/baselines_DEPRL/myoLegWalk_20230514/myoLeg/config.yaml

@@ -0,0 +1,22 @@
+tonic:
+  after_training: ''
+  agent: deprl.custom_agents.dep_factory(3, deprl.custom_mpo_torch.TunedMPO())(replay=deprl.replays.buffers.Buffer(return_steps=3, batch_size=256, steps_between_batches=1000, batch_iterations=30, steps_before_batches=2e5))
+  before_training: ''
+  checkpoint: last
+  environment: deprl.environments.Gym('myoLegWalk-v0', scaled_actions=False)
+  environment_name: relocate_test
+  header: import deprl, gym
+  sequential: 10
+  name: myoLeg
+  parallel: 20
+  seed: 0
+  test_environment: null
+  trainer: deprl.custom_trainer.Trainer(steps=int(1e8), epoch_steps=int(2e5), save_steps=int(1e6))
+env_args: {}
+working_dir: 'baselines_DEPRL/myoLegWalk_20230514/myoLeg/'
+mpo_args:
+  hidden_size: 1024
+  lr_actor: 3.53e-05
+  lr_critic: 6.081e-05
+  lr_dual: 0.00213
+