1
$\begingroup$

I was going through the chapter "Monte Carlo Methods" from the book "Reinforcement Learning" by Sutton and Barto. The author says that when a model is not available then it is useful to estimate action-values rather than state-value. But I am confused about what he means by a model.

Please refer to the screenshot below: enter image description here

Improve this question
$\endgroup$
0