Scheduling networks of queues: heavy traffic analysis of a simple open network
Queueing Systems: Theory and Applications
Heavy Traffic Analysis of a Controlled Multiclass Queueing Network via Weak Convergence Methods
SIAM Journal on Control and Optimization
Heavy Traffic Convergence of a Controlled, Multiclass Queueing System
SIAM Journal on Control and Optimization
On the existence of fixed points for approximate value iteration and temporal-difference learning
Journal of Optimization Theory and Applications
Neuro-Dynamic Programming
The Linear Programming Approach to Approximate Dynamic Programming
Operations Research
Convex Optimization
On Constraint Sampling in the Linear Programming Approach to Approximate Dynamic Programming
Mathematics of Operations Research
Maximum Pressure Policies in Stochastic Processing Networks
Operations Research
Learning tetris using the noisy cross-entropy method
Neural Computation
Mathematics of Operations Research
A Numerical Method for Solving Singular Stochastic Control Problems
Operations Research
Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics)
Dynamic Programming and Optimal Control, Vol. II
Dynamic Programming and Optimal Control, Vol. II
Constraint relaxation in approximate linear programs
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Tetris is hard, even to approximate
COCOON'03 Proceedings of the 9th annual international conference on Computing and combinatorics
Dynamic server allocation to parallel queues with randomly varying connectivity
IEEE Transactions on Information Theory
Pathwise Optimization for Optimal Stopping Problems
Management Science
Approximate Linear Programming for Average Cost MDPs
Mathematics of Operations Research
Hi-index | 0.00 |
We present a novel linear program for the approximation of the dynamic programming cost-to-go function in high-dimensional stochastic control problems. LP approaches to approximate DP have typically relied on a natural “projection” of a well-studied linear program for exact dynamic programming. Such programs restrict attention to approximations that are lower bounds to the optimal cost-to-go function. Our program---the “smoothed approximate linear program”---is distinct from such approaches and relaxes the restriction to lower bounding approximations in an appropriate fashion while remaining computationally tractable. Doing so appears to have several advantages: First, we demonstrate bounds on the quality of approximation to the optimal cost-to-go function afforded by our approach. These bounds are, in general, no worse than those available for extant LP approaches and for specific problem instances can be shown to be arbitrarily stronger. Second, experiments with our approach on a pair of challenging problems (the game of Tetris and a queueing network control problem) show that the approach outperforms the existing LP approach (which has previously been shown to be competitive with several ADP algorithms) by a substantial margin.