Theoretical and Numerical Analysis of Approximate Dynamic Programming with Approximation Errors

This study is aimed at answering the famous question of how the approximation errors at each iteration of Approximate Dynamic Programming (ADP) affect the quality of the final results considering the fact that errors at each iteration affect the next iteration. To this goal, convergence of Value Iteration scheme of ADP for deterministic nonlinear optimal control problems with undiscounted cost functions is investigated while considering the errors existing in approximating respective functions. The boundedness of the results around the optimal solution is obtained based on quantities which are known in a general optimal control problem and assumptions which are verifiable. Moreover, since the presence of the approximation errors leads to the deviation of the results from optimality, sufficient conditions for stability of the system operated by the result obtained after a finite number of value iterations, along with an estimation of its region of attraction, are derived in terms of a calculable upper bound of the control approximation error. Finally, the process of implementation of the method on an orbital maneuver problem is investigated through which the assumptions made in the theoretical developments are verified and the sufficient conditions are applied for guaranteeing stability and near optimality.
Comment: This study is the counterpart of another work of the author (arXiv:1412.5675) which was for value iterations with initial stabilizing guess (with overlaps on Theorem 1 and Lemma 1). As for the revision on this work, some steps of proofs are updated and an explanation about the approximation error is included. Initial submission date: 12/18/2014