Function discount_with_dones

rl3/a2c/a2c.py:30–36

(rewards, dones, gamma)

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