Motivated by (approximate) dynamic programming and model predictive control problems, we analyse the stability of deterministic nonlinear discrete-time systems whose inputs minimize a discounted finite-horizon cost. We assume that system satisfies stabilizability detectability properties with respect to stage Then, Lyapunov function for closed-loop is constructed uniform semiglobal property ens...

We address the problem of learning robot control by model-free reinforcement learning (RL). We adopt the probabilistic model of Vlassis and Toussaint (2009) for model-free RL, and we propose a Monte Carlo EM algorithm (MCEM) for control learning that searches directly in the space of controller parameters using information obtained from randomly generated robot trajectories. MCEM is related to,...

This paper discusses why the selection of a finite planning horizon is preferable to an infinite one for a replenishment policy of production inventory models. In a production inventory model, the production rate is dependent on both the demand rate and the inventory level. When there is an exponentially decreasing demand, the application of an infinite planning horizon model is not suitable. T...