Sep 6, 2018 · 1 min read
Great post ! Just one question, how do we calculate V(s) ? Do we take the max of the Q(s,a) for every state,action that we take at said state while playing the game or is there something I’m missing out ?
Great post ! Just one question, how do we calculate V(s) ? Do we take the max of the Q(s,a) for every state,action that we take at said state while playing the game or is there something I’m missing out ?