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
Proceedings ArticleDOI
Toward intelligent decision support for security staff: evaluation of an interactive resource management system based on a CMDP model
TL;DR: An evaluation of the CMDP-based decision support shows that displaying both resource allocation recommendation and risk map enables the participants to handle threat scenarios more cost-saving, and additionally causes less workload and higher acceptance among the participants.
Proceedings ArticleDOI
An approximate dynamic programming model for link scheduling in WMNs with gateway design constraint
TL;DR: The experiment results show that, in addition to maintaining many wireless network characteristics, the scheduling algorithm is effectively executed and approximate dynamic programming effectively simulates dynamic programming and has performances superior to genetic algorithm.
Posted Content
Energy-Efficient Transmission Scheduling with Strict Underflow Constraints
TL;DR: In this paper, the authors consider a single source transmitting data to one or more receivers/users over a shared wireless channel and show that a modified base-stock policy is optimal under the finite horizon, infinite horizon discounted, and infinite horizon average expected cost criteria.
Journal ArticleDOI
Likelihood-Based Inference in Data Envelopment Analysis
TL;DR: Two methods are proposed which are consistent with the data-generating-process implied by DEA and MCMC algorithms are proposed and implemented for both methods in the context of arti cial and real data.
Proceedings ArticleDOI
Optimal power allocation over multiple identical Gilbert-Elliott channels
TL;DR: In this article, an optimal power allocation policy that maximizes the expected discounted number of bits transmitted over an infinite time span was derived for a three-channel communication system with time varying channel qualities.
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.