Update 4.prioritized dqn.ipynb

[jsrimr]

removed volatile parameter and added wrapper @torch.no_grad()
zip(*samples) -> list(zip(*samples))
.data[0] -> .item() . # 2 cases

[Deepakgthomas]

Hi @jsrimr,

While running the prioritized dqn, I came across this error - TypeError: 'zip' object is not subscriptable

I guess your solution of zip(*samples) -> list(zip(*samples)) works. But the author was able to run his code without any modification and still gets results. Do you know how that was possible?