Goal-Conditioned Distance

Problem

Compute the Euclidean distance between a state and a goal vector. Return the square root of the sum of squared differences.

Hint

Goal-conditioned rewards are often the negative of this distance.

case 1

in: [[0,0],[3,4]]

expected: 5

case 2

in: [[1,2],[1,2]]

expected: 0

case 3

in: [[-1,-1],[2,3]]

expected: 5

case 4

in: [[1,1,1],[1,1,1]]

expected: 0

Starter codePython

import math
def goal_conditioned_distance(state, goal):
    # Your code here
    pass

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