Target Networks: Slow and Steady Wins the Race

Photo by Possessed Photography on Unsplash

Reinforcement Learning is the third family of Machine Learning algorithms, after supervised and unsupervised learning. The aim is to find optimal behavior in an environment through interactions and learning from them. In a perfect world, we can efficiently measure the state of the environment, predict the outcome of each of our actions, and know their exact value. These problems were solved through Dynamic…