To remove the limitation of short-term memory, Zhen et al.

While this has been demonstrated empirically overtimeinavarietyoftasks,theoretical resultsquantifying thebenefits of such methods are still few and far between. In this paper, we discuss the kind of structure in a Markov decision process which gives rise to efficient HRLmethods.

We consider here the sparse Gaussian process regression (SGPR) approach introduced by Titsias [31], which is widely used in practice (see [1, 9] for implementations) and has been studied in many recent works [13,21,5,6,38,28,32,22,23].

Neural ordinary differential equations are an attractive option for modelling temporal dynamics. However, a fundamental issue is that the solution to an ordinary differential equation is determined by its initial condition, and there is no mechanism for adjusting the trajectory based on subsequent observations. Here, we demonstrate how this may be resolved through the well-understood mathematics of controlled differential equations.