2
$\begingroup$

In reinforcement learning, when we talk about the principle of optimality, do we assume the policy to be deterministic?

$\endgroup$
4
  • $\begingroup$ Hi. Can you clarify what your question is? Is it "when we talk about the principle of optimality, do we assume policy to be deterministic?" $\endgroup$
    – nbro
    Aug 18, 2020 at 10:14
  • $\begingroup$ Yes, that's what I meant $\endgroup$ Aug 18, 2020 at 10:17
  • $\begingroup$ Which "principle of optimality" are you talking about exactly? Where did you read this term? Maybe provide a reference to the book? Are you talking about the optimality of the value iteration and/or policy iteration? I heard the term "principle of optimality" only in the context of dynamic programming algorithms. $\endgroup$
    – nbro
    Aug 18, 2020 at 10:19
  • $\begingroup$ Yes, I'm reading Sutton-Barto, Introduction to Reinforcement learning. I'm asking in the context of DP only. $\endgroup$ Aug 18, 2020 at 10:22

0

You must log in to answer this question.

Browse other questions tagged .