Reinforcement Learning

Five questions. Choose one answer for each, then submit to see your score and explanations.

The practice target is 80%. You can retry as often as you like, and every lesson stays accessible.

You can practice as a guest. Sign in before starting an attempt to save your scores.

1. Which explanation matches actions, states, and rewards?A. A Markov decision process models transitions and delayed cumulative rewards under its state assumption.B. A reinforcement-learning problem has states, actions, rewards, and a policy choosing actions.C. A value estimate summarizes expected future reward under a policy or action.D. Exploration gathers information; exploitation chooses the currently preferred action.

2. Which explanation matches delayed feedback in a markov decision process?A. A Markov decision process models transitions and delayed cumulative rewards under its state assumption.B. A reinforcement-learning problem has states, actions, rewards, and a policy choosing actions.C. A value estimate summarizes expected future reward under a policy or action.D. Exploration gathers information; exploitation chooses the currently preferred action.

3. Which explanation matches estimate values from experience?A. A reinforcement-learning problem has states, actions, rewards, and a policy choosing actions.B. A Markov decision process models transitions and delayed cumulative rewards under its state assumption.C. Exploration gathers information; exploitation chooses the currently preferred action.D. A value estimate summarizes expected future reward under a policy or action.

4. For delayed feedback in a markov decision process, which result or action fits this practical case: A reroute saves time today but affects later driver availability.A. Define state before departure, a reroute action, and a later on-time reward.B. Update an estimate from experience while tracking how much evidence supports it.C. Compare the immediate travel-time effect with later schedule consequences.D. Try a limited, monitored experiment rather than rerouting every critical delivery at once.

5. For balance exploration with safe decisions, which result or action fits this practical case: A new route might be faster but has little evidence.A. Define state before departure, a reroute action, and a later on-time reward.B. Try a limited, monitored experiment rather than rerouting every critical delivery at once.C. Compare the immediate travel-time effect with later schedule consequences.D. Update an estimate from experience while tracking how much evidence supports it.

Review this module from its first lesson →

Reinforcement Learning

Your result