Discrete SAC Entropy Target

Problem

Compute the discrete SAC target entropy: 0.98 * ln(n_actions).

Hint

A fraction of the maximum entropy keeps the policy from collapsing too early.

case 1

in: [4]

expected: 1.3585684738974928

case 2

in: [2]

expected: 0.6792842369487464

case 3

in: [10]

expected: 2.2565333911341647

Starter codePython

import math
def discrete_sac_entropy_target(n_actions):
    # Your code here
    pass

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