Now that we've reached the end of this book, you are in a great position to continue your study of Q-learning with a wealth of knowledge on how to approach RL problems and develop solutions to them as part of the broader community of RL researchers and practitioners. We've provided some additional study resources in the Further reading section.
One of the most important things we want to be able to do as RL researchers is track the progress of our own research and compare it to the work of other researchers at other institutions, working under different research methodologies. Tracking progress in RL research is made difficult by the fact that different implementations of environments can lead to large discrepancies in the difficulty level of implementing a solution to an RL task.
As a solution to this discipline-wide problem, OpenAI Gym provides a variety of...