Image courtesy of


I recently took a dive into deep reinforcement learning and wanted to share what I have learned along the way. To do this I am putting together a series of tutorials to illustrate the variety of deep RL algorithms and their differences. Each post will feature a discussion of the algorithm as well as a link to an implementation showing how to translate the theory into code. Future posts will cover imitaton learning, policy gradients, natural policy gradients, off-policy learning, task generalization, and more. Stay tuned!