In all, reinforcement learning suffers from the same limitations as regular machine learning. It’s an ideal option for domains that are evolving and where some data is unavailable at the start.

Scientists at U.K.-based AI lab DeepMind argue true artificial intelligence will emerge from sticking to the principle of reward maximization.

Reinforcement learning techniques could be the keys to integrating robots — who use machine learning to output more than words — into the real world.

One last thing you need to know: machine (and deep) learning comes in three flavors: supervised, unsupervised, and reinforcement. In supervised learning, the most prevalent, the data is labeled to ...