1 min readApr 26, 2020
Hi, Q-function is the expected reward from state s and after choosing action a. A Value function is the expected reward from state s before choosing an action. Same thing about the r. Hope this clears things.
Hi, Q-function is the expected reward from state s and after choosing action a. A Value function is the expected reward from state s before choosing an action. Same thing about the r. Hope this clears things.
Lives in Tel-Aviv, Israel 🇮🇱 See me on shakedzy.xyz