updated code

README.md

@@ -30,8 +30,53 @@ TODO: Add your code
 
 
 ```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+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
+
+#Environment 1: AntBulletEnv-v0
+env_id = "AntBulletEnv-v0"
+# Create the env
+env = gym.make(env_id)
+
+env = make_vec_env(env_id, n_envs=4)
+
+# Adding this wrapper to normalize the observation and the reward
+env = VecNormalize(env, norm_obs=True, norm_reward=True, clip_obs=10)
+
+#create A2C model
+model = A2C(policy = "MlpPolicy",
+            env = env,
+            gae_lambda = 0.9,
+            gamma = 0.99,
+            learning_rate = 0.00096,
+            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 agent
+model.learn(1_500_000)
+
+# Save the model and VecNormalize statistics when saving the agent
+model.save("a2c-AntBulletEnv-v0")
+env.save("vec_normalize.pkl")
 ```