This blog looks at using model-based methods to solve classic control problems in OpenAI gym. Some of these methods use deep learning, but no RL allowed!
View the Project on GitHub davebiagioni/sketches-in-rl-free-classic-control
Testing…
This is some inline math: \(y = f(x)\)
This is a matrix:
\[M = \left( \begin{array}{ccc} x_{11} & x_{12} & \ldots \\ x_{21} & x_{22} & \ldots \\ \vdots & \vdots & \ldots \\ \end{array} \right)\]This is some code:
def f(x: float) -> float:
return x**2