When it is not possible to determine a policy that is greedy with respect to the value functions v π , q π (Select all that apply).

Question

When it is not possible to determine a policy that is greedy with respect to the value functions v π , q π  (Select all that apply).

Answer

When action values q π   are available but no model is available

Answer

When state values v π   are available but no model is available

Answer

When action values q π   and a model are available

Answer

When state values v π   and model are available

Crowdly