Seperate learner and worker parallelly

[jinPrelude]

Although current training speed is not bad it takes almost a month(2,685,280s) to train IQN for 200M frames in atari environment, So if separating training part and worker parallelly as mentioned on the blog linked below could speed up the process it would be worth trying.

https://medium.com/@shmuma/speeding-up-dqn-on-pytorch-solving-pong-in-30-minutes-81a1bd2dff55