DRL documentation

[RaulFdzbis]

So a documentation should be done about how to use DRL with the code presented in xgnitive. Not only how to perform the train, but also how to use the created environments, and differents how this code works related things.

My idea is that this is not intended to be a rllab manual but more a guide to have a high level understanding of how this code works.

[RaulFdzbis]

working on https://github.com/roboticslab-uc3m/xgnitive/blob/develop/programs/drl/documentation/How-to-rllab.md

[RaulFdzbis]

Finished v1: https://github.com/roboticslab-uc3m/xgnitive/blob/db54813ab2204777362f0eccfbd933061d767949/programs/drl/documentation/How-to-rllab.md

As an initial version may be a lot of errors, and incomplete things, if you can spot any just let me know!

The next step is : "How to use the DRL code in xgnitive" as a just more practical way to document how to execute the different programs without a previous knowledge of how rllab works.

I also have related documentation about:

• Theano.
• Create a new algorithm in rllab.

However since right now this is out of the scope of our work, i will give a low priority to both of this documentations. If someone is interested, please let me know, i could give them more priority.

[RaulFdzbis]

Finished: https://github.com/roboticslab-uc3m/xgnitive/blob/develop/programs/drl/README.md

[jgvictores]

Blocks #60