1. How would you rank DQN, A2C, and ES based on their sample efficiency?
2. What would their rank be if they were rated on the training time and 100 CPUs were available?
3. Would you start debugging an RL algorithm on CartPole or MontezumaRevenge?
4. Why is it better to use multiple seeds when comparing multiple deep RL algorithms?

5. Does the intrinsic reward help with the exploration of an environment?
6. What's transfer learning?