Update README.md

README.md

@@ -30,8 +30,65 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
 
+%%capture
+!apt install python-opengl
+!apt install ffmpeg
+!apt install xvfb
+!pip3 install pyvirtualdisplay
+
+
+from pyvirtualdisplay import Display
+
+virtual_display = Display(visible=0, size=(1400, 900))
+virtual_display.start()
+
+!pip install stable-baselines3[extra]
+!pip install gymnasium
+!pip install huggingface_sb3
+!pip install huggingface_hub
+!pip install panda_gym
+
+import os
+
+import gymnasium as gym
+import panda_gym
+from stable_baselines3 import A2C
+from stable_baselines3.common.evaluation import evaluate_policy
+from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
+from stable_baselines3.common.env_util import make_vec_env
+
+env_id = "PandaPickAndPlace-v3"
+
+env = gym.make(env_id)
+env = make_vec_env(env_id, n_envs=4)
+env = VecNormalize(env, clip_obs = 10)
+model = A2C("MultiInputPolicy", env, verbose=1)
+model.learn(1_000_000)
+
+model.save("a2c-PandaPickAndPlace-v3")
+env.save("vec_normalize.pkl")
+
+
+from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
+
+# Load the saved statistics
+eval_env = DummyVecEnv([lambda: gym.make("PandaPickAndPlace-v3")])
+eval_env = VecNormalize.load("vec_normalize.pkl", eval_env)
+
+# We need to override the render_mode
+eval_env.render_mode = "rgb_array"
+
+#  do not update them at test time
+eval_env.training = False
+# reward normalization is not needed at test time
+eval_env.norm_reward = False
+
+# Load the agent
+model = A2C.load("a2c-PandaPickAndPlace-v3")
+
+mean_reward, std_reward = evaluate_policy(model, eval_env)
+
+print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
 ...
 ```