Rollout generation with horizon time steps

assigned to @dl337788

changed milestone to %Official dates

added Bug label

added In Progress label

Use done == True to create a mask that cuts off returns and advantages in terminal states

mentioned in commit e887112e

mentioned in commit 99ac3d9a

mentioned in commit 93b039c0

added In Review label and removed In Progress label

marked this issue as related to #60 (closed)

closed

removed In Review label