30. Quiz: Action-Value Functions

Quiz: Action-Value Functions

True or False?: For a deterministic policy \pi,

v_\pi(s) = q_\pi(s, \pi(s))

holds for all s \in \mathcal{S}.

Feel free to use the state-value and action-value functions (for an example deterministic policy) above to answer this question.

Is the above statement true or false?

SOLUTION: True