should dqn state values need to be 0 to 1 only

Question

should the values of the state in DQN need to be only 0 to 1 for example state = [0, 0, 0, 1, 1, 1, 1, 0, 1, 0]

or it can have a state with values greater than 1 eh state = [6, 5, 4, 1, 1, 1, 2, 3, 15, 10]

States have never been limited in value, what makes you ask this? — Dr. Snoopy, May 25 '20 at 14:46

score 1 · Accepted Answer · answered May 26 '20 at 15:45

States per se need not be limited in value. You can have as big a range as you want. But for training purposes, it is recommended to normalise the state values in a range [0,1] so that the neural network used a function approximation does not saturate.

should dqn state values need to be 0 to 1 only

1 Answers1