Reinforcement learning is known to be unstable or even to diverge when a nonlinear function approximator such as a neural network is used to represent the action-value known as Q function.
Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network is computed using a black- box differential equation solver.
A SIR model is an epidemiological model that calculates the theoretical number of people infected with a contagious disease in a closed population over time.
