Thinking deeply about Reinforcement Learning

Remember reading about reinforcement learning, having designed more mundane neural network deep learning,  and thinking, but how do you design the 'objective function' to drive its action? 

Nicely constrained and goal oriented.  Below, from O'Reilly,  " ... A must-read series of posts by Ben Recht "unpacks what is legitimately interesting and promising in RL and what is probably just hype.".  ... Following.

Make It Happen    nbvcxz By Benjamin Recht  

This is the first part of “An Outsider’s Tour of Reinforcement Learning.” Part 2 is linked to.

If you read hacker news, you’d think that deep reinforcement learning can be used to solve any problem. Deep RL has claimed to achieve superhuman performance on Go, beat atari games, control complex robotic systems, automatically tune deep learning systems, manage queueing in network stacks, and improve energy efficiency in data centers. What a miraculous technology! I personally get suspicious when audacious claims like this are thrown about in press releases, and I get even more suspicious when other researchers call into question their reproducibility. I want to take a few posts to unpack what is legitimately interesting and promising in RL and what is probably just hype. I also want to take this opportunity to argue in favor of more of us working on RL: some of the most important and pressing problems in machine learning are going to require solving exactly the problems RL sets out to solve.  .... "