Transfer learning is all the rage in the machine learning community these days. It serves as the basis for many of the managed AutoML services and now figures prominently in the latest NLP research. We’re also starting to see examples of neural networks that can handle multiple tasks using transfer learning across domains. The main question at hand is: could transfer learning have applications within reinforcement learning? Compared to other machine learning methods, deep reinforcement learning has a reputation for being data hungry, subject to instability in its learning process.