The Linear Programming Approach to Approximate Dynamic Programming
TLDR
In this article, an efficient method based on linear programming for approximating solutions to large-scale stochastic control problems is proposed. But the approach is not suitable for large scale queueing networks.Abstract:
The curse of dimensionality gives rise to prohibitive computational requirements that render infeasible the exact solution of large-scale stochastic control problems. We study an efficient method based on linear programming for approximating solutions to such problems. The approach "fits" a linear combination of pre-selected basis functions to the dynamic programming cost-to-go function. We develop error bounds that offer performance guarantees and also guide the selection of both basis functions and "state-relevance weights" that influence quality of the approximation. Experimental results in the domain of queueing network control provide empirical support for the methodology.read more
Citations
More filters
Posted Content
Robust Bayesian reinforcement learning through tight lower bounds
TL;DR: In this paper, a lower bound on the utility of a near-optimal memoryless policy for the decision problem is derived, which is different from both the Bayes optimal policy and the policy which is optimal for the expected MDP under the current belief.
Journal ArticleDOI
Semi-Infinite Relaxations for the Dynamic Knapsack Problem with Stochastic Item Sizes
TL;DR: A new semi-infinite relaxation based on an affine value function approximation is proposed, and it is shown that an existing pseudo-polynomial relaxation corresponds to a nonparametricvalue function approximation.
Journal ArticleDOI
An Approximate Dynamic Programming Approach to Dynamic Pricing for Network Revenue Management
Jiannan Ke,Dan Zhang,Huan Zheng +2 more
TL;DR: This paper considers a dynamic programming model and uses approximate linear programs (ALPs) to solve the problem and reports numerical results on computational and policy performance on a set of hub-and-spoke problem instances.
Book ChapterDOI
Chapter 22 Duality Theory and Approximate Dynamic Programming for Pricing American Options and Portfolio Optimization
Martin B. Haugh,Leonid Kogan +1 more
TL;DR: This chapter describes how duality and approximate dynamic programming (ADP) methods can be used in financial engineering and focuses on American option pricing and portfolio optimization problems when the underlying state space is high-dimensional.
Journal ArticleDOI
Approximate Linear Programming for Average Cost MDPs
TL;DR: Bounds are derived for average cost error and performance of the policy generated from the LP that involve the mixing time of the Markov decision process MDP under this policy or the optimal policy, improving on a previous performance bound involving mixing times.
References
More filters
Book
Reinforcement Learning: An Introduction
TL;DR: This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Book
Neural networks for pattern recognition
TL;DR: This is the first comprehensive treatment of feed-forward neural networks from the perspective of statistical pattern recognition, and is designed as a text, with over 100 exercises, to benefit anyone involved in the fields of neural computation and pattern recognition.
Book
Dynamic Programming and Optimal Control
TL;DR: The leading and most up-to-date textbook on the far-ranging algorithmic methododogy of Dynamic Programming, which can be used for optimal control, Markovian decision problems, planning and sequential decision making under uncertainty, and discrete/combinatorial optimization.
Journal ArticleDOI
Learning to Predict by the Methods of Temporal Differences
TL;DR: This article introduces a class of incremental learning procedures specialized for prediction – that is, for using past experience with an incompletely known system to predict its future behavior – and proves their convergence and optimality for special cases and relation to supervised-learning methods.
Book
Neuro-dynamic programming
TL;DR: This is the first textbook that fully explains the neuro-dynamic programming/reinforcement learning methodology, which is a recent breakthrough in the practical application of neural networks and dynamic programming to complex problems of planning, optimal decision making, and intelligent control.