add code

README.md

@@ -30,8 +30,82 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+#install
+!apt install python-opengl
+!apt install ffmpeg
+!apt install xvfb
+!pip3 install pyvirtualdisplay
+!pip install -r https://raw.githubusercontent.com/huggingface/deep-rl-class/main/notebooks/unit6/requirements-unit6.txt
 
+# Virtual display
+from pyvirtualdisplay import Display
+virtual_display = Display(visible=0, size=(1400, 900))
+virtual_display.start()
+
+#imports
+import pybullet_envs
+import panda_gym
+import gym
+
+import os
+
+from huggingface_sb3 import load_from_hub, package_to_hub
+
+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
+
+from huggingface_hub import notebook_login
+
+#Define the environment called "PandaReachDense-v2"
+env_id = "PandaReachDense-v2"
+
+#Make a vectorized environment
+env = make_vec_env(env_id, n_envs=4)
+
+#Add a wrapper to normalize the observations and rewards. Check the documentation
+env = VecNormalize(env, norm_obs=True, norm_reward=True, clip_obs=10)
+
+#Create the A2C Model (don't forget verbose=1 to print the training logs).
+model = A2C(policy = "MultiInputPolicy",
+            env = env,
+            gae_lambda = 0.9,
+            gamma = 0.95,
+            learning_rate = 0.001,
+            max_grad_norm = 0.5,
+            n_steps = 8,
+            vf_coef = 0.4,
+            ent_coef = 0.0,
+            seed=11,
+            policy_kwargs=dict(
+            log_std_init=-2, ortho_init=False),
+            normalize_advantage=False,
+            use_rms_prop= True,
+            use_sde= True,
+            verbose=1)
+
+#Train it for 1M Timesteps
+model.learn(1_500_000)
+
+#Save the model and VecNormalize statistics when saving the agent
+model.save(f"a2c-{env_id}")
+env.save(f"vec_normalize_{env_id}.pkl")
+
+#Evaluate your agent
+eval_env = DummyVecEnv([lambda: gym.make(env_id)])
+eval_env = VecNormalize.load(f"vec_normalize_{env_id}.pkl", eval_env)
+
+#  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 model
+model = A2C.load(f"a2c-{env_id}")
+
+#Evaluate model
+mean_reward, std_reward = evaluate_policy(model, eval_env)
+print(f"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}")
 ...
 ```