We describe the reinforcement learning problem, motivate algorithms which seek an approximation to the Q function, and present new convergence results for two such algorithms.

In this paper, we address the problem of how to seamlessly and without repetition artifacts or visible projective distortion cover the surface of a polygonally-defined model with a texture pattern derived from an acquired 2D image such that the dominant orientation of the pattern will everywhere follow the surface shape in an aesthetically pleasing way. Specifically, we propose an efficient, au...

This paper is about the study of B-FQI, an Approximated Value Iteration (AVI) algorithm that exploits a boosting procedure to estimate the action-value function in reinforcement learning problems. B-FQI is an iterative off-line algorithm that, given a dataset of transitions, builds an approximation of the optimal action-value function by summing the approximations of the Bellman residuals acros...

An optimized embedded 5(3) pair of explicit Runge–Kutta–Nyström methods with four stages using phase-fitted and amplification-fitted techniques is developed in this paper. The new adapted can exactly integrate (except round-off errors) the common test: y?=?w2y. local truncation error method derived, we show that order convergence maintained. stability analysis addressed, demonstrate absolutely ...