def discount_with_dones()

in maddpg/trainer/maddpg.py [0:0]

• 8 lines of code
• 2 McCabe index (conditional complexity)

def discount_with_dones(rewards, dones, gamma):
    discounted = []
    r = 0
    for reward, done in zip(rewards[::-1], dones[::-1]):
        r = reward + gamma*r
        r = r*(1.-done)
        discounted.append(r)
    return discounted[::-1]