Bounded Approximate Symbolic Dynamic Programming for Hybrid MDPs
Abstract
Recent advances in symbolic dynamic programming (SDP) combined with the extended algebraic decision diagram (XADD) data structure have provided exact solutions for mixed discrete and continuous (hybrid) MDPs with piecewise linear dynamics and continuous actions. Since XADD-based exact solutions may grow intractably large for many problems, we propose a bounded error compression technique for XADDs that involves the solution of a constrained bilinear saddle point problem. Fortuitously, we show that given the special structure of this problem, it can be expressed as a bilevel linear programming problem and solved to optimality in finite time via constraint generation, despite having an infinite set of constraints. This solution permits the use of efficient linear program solvers for XADD compression and enables a novel class of bounded approximate SDP algorithms for hybrid MDPs that empirically offers order-of-magnitude speedups over the exact solution in exchange for a small approximation error.
Cite
@article{arxiv.1309.6871,
title = {Bounded Approximate Symbolic Dynamic Programming for Hybrid MDPs},
author = {Luis Gustavo Vianna and Scott Sanner and Leliane Nunes de Barros},
journal= {arXiv preprint arXiv:1309.6871},
year = {2013}
}
Comments
Appears in Proceedings of the Twenty-Ninth Conference on Uncertainty in Artificial Intelligence (UAI2013)