Questions

1. How can you modify an environment or add additional environments to the Gym package?
2. Why have we chosen to use the terms state and observation interchangeably in this context?
3. What does env.reset() do and what does it return?
4. Under what conditions does the game loop that we created exit?
5. What variable do we set to manually change the state of the environment?
6. Why does a randomly-acting agent usually take longer than a learning agent to reach a destination?