Action Normalization

Problem

Normalize a continuous action from [low, high] into [-1, 1]: 2 * (action - low) / (high - low) - 1.

Hint

The normalized action is what tanh-squashed policies output.

case 1

in: [0,-1,1]

expected: 0

case 2

in: [1,-1,1]

expected: 1

case 3

in: [-1,-1,1]

expected: -1

case 4

in: [2.5,0,5]

expected: 0

Starter codePython

def action_normalization(action, low, high):
    # Your code here
    pass

4 test cases · run your code against them in the editor