Deep reinforcement learning (DRL) is one promising approach to teaching robots perform complex tasks. Because methods that directly reuse the stored experience data cannot follow change of environment in robotic problems with a time-varying environment, online DRL required. The eligibility traces method well known as an technique for improving sample efficiency traditional linear regressors rat...

in this paper, the bernstein polynomials are used to approximate the solutions of linear integral equations with multiple time lags (iemtl) through expansion methods (collocation method, partition method, galerkin method). the method is discussed in detail and illustrated by solving some numerical examples. comparison between the exact and approximated results obtained from these methods is...