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
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation
TL;DR: Several new algorithms for learning Markov Decision Processes in an infinite-horizon average-reward setting with linear function approximation with inspiration from adversarial linear bandits are developed.
Journal ArticleDOI
Approximate dynamic programming approach for process control
Jay H. Lee,Wee Chin Wong +1 more
TL;DR: It is argued that ADP possesses great potentials, especially for obtaining effective control policies for stochastic constrained nonlinear or linear systems and continually improving them towards optimality.
Book ChapterDOI
Factored Markov Decision Processes
Thomas Degris,Olivier Sigaud +1 more
TL;DR: The idea of factored representations is that some part of this huge state do not depend on each other and that this structure can be exploited to derive a more compact representation of the global state and obtain more efficiently an optimal policy.
Dissertation
Computational methods for static allocation and real-time redeployment of ambulances
TL;DR: A specially tailored approximation architecture for the dynamic-redeployment problem, using the previously developed approximation architecture, concludes that, although the policies obtained are comparable in quality to those obtained using regression, there are serious issues related to numerical stability.
Journal ArticleDOI
Investments in combined cycle natural gas-fired systems: A real options analysis
TL;DR: This study analyses different real options approaches for making investment decisions in the energy sector and concludes that a real options approach that fails to capture the uncertainty of all the periods and proposes a process that determines directly the uncertainty associated with the first period can be considered fair.
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.