# Exploration-Exploitation > Stochastic Gradient Descent (SGD), [the workhorse learning algorithm of Deep Learning](https://medium.com/intuitionmachine/the-deeply-suspicious-nature-of-backpropagation-9bed5e2b085e), are algorithms that employ exploitation as its fundamental motivation. SGD works only for networks that are composed of differentiable layers. Convergence happens because there will be regimes in the parameter space that guarantee convergence of iterative affine transformations. This is well known in other fields such as [Control Theory](https://en.wikipedia.org/wiki/Control_theory) (known as Method of Adjoints) as well as in Chaos theory (Iterated Function Systems). --- Date: 20211117 Links to: [Reinforcement Learning (old)](Reinforcement%20Learning%20(old).md) [Backpropagation](Backpropagation.md) Tags: References: * [Deep Learning and Exploration vs. Exploitation](https://medium.com/intuitionmachine/exploration-exploitation-and-imperfect-representation-in-deep-learning-9472b67fdecd)