Please consider donating to help support future tutorials, articles, and implementations. Any contribution is greatly appreciated!
Learning Policies For Learning Policies — Meta Reinforcement Learning (RL²) in Tensorflow
Arthur Juliani

Hey Arthur. I really enjoy all of your articles. You have a very engaging style that makes the material accessible.

I’ve been writing a series of stories that are proving very popular, Learning AI if You Suck at Math. It resonates because a lot of people are great sys-admins or programmers but never really needed math. Now they’d like to know more about this field. I see the next wave of innovation coming from this group of folks. As Francois Chollet said to me, deep learning is relatively mature but it’s not widely disseminated. We need need to democratize AI. So it makes sense to turn this concept into a book, but I can’t do it alone. You’re the first one I thought of, as a co-author possibility.

The market is wide open right now on Deep Learning. Other than Goodfellow’s book, which is inaccessible to beginners, there are a few books on the way, but they are still pre-orders.

It’s likely we could even re-purpose a lot of what we’ve already written. We could give it some order and purpose, fill in some blanks, get a Github going and offer some code. Frankly, I’m a terrible coder, but a pretty damn good writer at this point. Teaching people AI requires a balance of skills.

Anyway, if you’re interested in exploring the idea, no commitments at this point of course, just ping me via email: dan [AT] We’ll talk it through and see if it makes sense. Cheers.

All the best,

Dan Jeffries

Like what you read? Give Daniel Jeffries a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.