Reward Clipping

Problem

Clip every reward into [-clip_value, clip_value]. An empty list returns [].

Hint

Clipping keeps large rewards from dominating the value targets.

case 1

in: [[0.5,2,-3],1]

expected: [0.5,1,-1]

case 2

in: [[5,-5],2]

expected: [2,-2]

case 3

in: [[],1]

expected: []

Starter codePython

def clip_rewards(rewards, clip_value):
    # Your code here
    pass

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