Match the algorithm name to its correct update rule (select all that apply)

Which of the following well-describe Temporal Difference (TD) and Monte-Carlo (MC) methods? (Select all that apply)

What is the target policy in Q-learning?

In an episodic setting, we might have different updates depending on whether the next state is terminal or non-terminal. Which of the following TD error calculations are correct? (Select all that apply)

Q-Learning needs to wait until the end of an episode before performing its update.

When using the Q-Learning update rule, how is the next action-value estimate determined?

Which parameter is used to control the balance between single-step and multi-step bootstrapping methods?

Sarsa, Q-learning, and Expected Sarsa have different targets on a transition to a terminal state.

Which of the following pairs is the correct characterization of the TD(0) and Monte-Carlo (MC) methods?