change the get_screen method so that it does not fill the gpu memory

[andreistirb]

I changed the get_screen method so that it does not copy the tensor to GPU device at the return point of the method. If we copy the tensor each and every time to the device at some point we would fill the memory with unnecessary data.
Also, in order for this to work I changed the forward method from the DQN object so that it copies the input to device before doing any other stuff.

[netlify]

Deploy preview for pytorch-tutorials-preview ready!

Built with commit 24a53a5

https://deploy-preview-415--pytorch-tutorials-preview.netlify.app

[soumith]

cc: @mike7ant

[facebook-github-bot]

Hi @andreistirb!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@fb.com. Thanks!

[holly1238]

Hi @andreistirb! Can you sign the CLA agreement so that I can merge the pull request? Thanks!

[andreistirb]

Hello @holly1238, I have completed the form, thank you for accepting my contribution!

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Facebook open source project. Thanks!