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 Article
Creating long gait animation sequences through Reinforcement Learning
Marco Alamia,N. Alberto Borghese +1 more
TL;DR: This paper presents how, using a careful definition of a state function, long animation sequences can be created joining clips from a database by a controller optimizing a cost function on the state function.
Linear programming and other mathematical methods applied to modelling business process optimisation
Posted ContentDOI
Geometric Programming Approximation to Dynamic Programming
TL;DR: In this article , the authors developed a geometric programming approximation to dynamic programming and obtained the optimal cost for decision making to be ₦97.30 and optimal decision policy to be (0.1, 0.2, 1, 3).
Proceedings ArticleDOI
Synthesis of Proactive Sensor Placement In Probabilistic Attack Graphs
TL;DR: In this article , the deployment of joint moving target defense (MTD) and deception against multi-stage cyber-attacks is studied. But the authors focus on the detection of the attack before the attacker achieves its objective.
Posted Content
More Efficient Exploration with Symbolic Priors on Action Sequence Equivalences
TL;DR: In this article, a new local exploration strategy is proposed to minimize collisions and maximize new state visitations by exploiting priors about action sequence equivalence, i.e., when different sequences of actions produce the same effect.
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.