OpenAI just announced the release of "Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning. Spinning Up consists of crystal-clear examples of RL code, educational exercises, documentation, and tutorials."

We didn't discuss neural net RL—presumably "deep" implies the use of a neural net—but exploring this resource would make an interesting project. Be aware, though, that this may require lots of trial and error work.

The announcement claims that little to no background knowledge is needed.

We were inspired to build Spinning Up through our work with the OpenAI Scholars and Fellows initiatives, where we observed that it’s possible for people with little-to-no experience in machine learning to rapidly ramp up as practitioners, if the right guidance and resources are available to them. Spinning Up in Deep RL was built with this need in mind and is integrated into the curriculum for 2019 cohorts of Scholars and Fellows.