Update index.md (#91)

docs/index.md

@@ -21,7 +21,7 @@ import gymnasium as gym
 env = gym.make("LunarLander-v2", render_mode="human")
 observation, info = env.reset(seed=42)
 for _ in range(1000):
-   action = policy(observation)  # User-defined policy function
+   action = env.action_space.sample()  # this is where you would insert your policy
    observation, reward, terminated, truncated, info = env.step(action)
 
    if terminated or truncated: