Bounds for multistage stochastic programs using supervised learning strategies

Authors:
Boris Defourny;Damien Ernst;Louis Wehenkel
Affiliations:
University of Liège, Systems and Modeling, Liège, Belgium;University of Liège, Systems and Modeling, Liège, Belgium;University of Liège, Systems and Modeling, Liège, Belgium
Venue:
SAGA'09 Proceedings of the 5th international conference on Stochastic algorithms: foundations and applications
Year:
2009

Citing 16
Cited 1

Regularization theory and neural networks architectures

Neural Computation
Barycentric scenario trees in convex multistage stochastic programming

Mathematical Programming: Series A and B
The connection between regularization operators and support vector kernels

Neural Networks
Markov Decision Processes: Discrete Stochastic Dynamic Programming

Markov Decision Processes: Discrete Stochastic Dynamic Programming
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Neuro-Dynamic Programming

Neuro-Dynamic Programming
Model Selection for Small Sample Regression

Machine Learning
Generating Scenario Trees for Multistage Decision Problems

Management Science
Tree-Based Batch Mode Reinforcement Learning

The Journal of Machine Learning Research
Relating reinforcement learning performance to classification performance

ICML '05 Proceedings of the 22nd international conference on Machine learning
The Scenario Generation Algorithm for Multistage Stochastic Linear Programming

Mathematics of Operations Research
Step decision rules for multistage stochastic programming: A heuristic approach

Automatica (Journal of IFAC)
Epi-convergent discretizations of multistage stochastic programs via integration quadratures

Mathematical Programming: Series A and B - Nonlinear convex optimization and variational inequalities
Scenario tree modeling for multistage stochastic programs

Mathematical Programming: Series A and B
Approximate policy iteration with a policy language bias: solving relational Markov decision processes

Journal of Artificial Intelligence Research
On complexity of multistage stochastic programs

Operations Research Letters

Scenario Trees and Policy Selection for Multistage Stochastic Programming Using Machine Learning

INFORMS Journal on Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a generic method for obtaining quickly good upper bounds on the minimal value of a multistage stochastic program. The method is based on the simulation of a feasible decision policy, synthesized by a strategy relying on any scenario tree approximation from stochastic programming and on supervised learning techniques from machine learning.