Update README.md

README.md

@@ -42,4 +42,11 @@ model = PPO.load(checkpoint)
 
 env = gym.make("LunarLander-v2")
 
+# Evaluate the agent and watch it
+eval_env = gym.make("LunarLander-v2")
+mean_reward, std_reward = evaluate_policy(
+    model, eval_env, render=True, n_eval_episodes=5, deterministic=True, warn=False
+)
+print(f"mean_reward={mean_reward:.2f} +/- {std_reward}")
+
 ```