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
A dynamic programming framework for optimal home scheduling
TL;DR: A dynamic programming framework for the optimal home scheduling problem involving rooftop solar generation, controllable loads, and battery storage is proposed, while considering uncertainties arising from solar generation and load forecasts.
OtherDOI
Reinforcement Learning
TL;DR: In reinforcement learning as mentioned in this paper , agents should take actions in an environment in order to maximize the notion of a so-called cumulative reward, which is a way of solving an optimal control problem without having a model of the environment.
Journal ArticleDOI
Optimal Utilization of Integrated Photovoltaic Battery Systems – An Application in Residential Sector
TL;DR: In this paper , a Markov Decision Process (MDP) model was developed to maximize the battery utilization subject to uncertainty in weather conditions and electricity demands, while accounting for battery degradation due to calendar aging and charging/discharging cycles.
Posted Content
Marginal Analysis of Perishable Inventory Models Using the Externality Principle
TL;DR: A new marginal analysis framework is developed to approximate this complex multiple-decision model into a single-Decision model with an externality term, which internalizes the long-term impact of ordering decisions.
Posted Content
Robust Online Selection with Uncertain Offer Acceptance.
TL;DR: In this paper, a secretary problem where a candidate may or may not accept an offer according to a known probability is considered, and the goal is to maximize a robust objective defined as the minimum over integers $k$ of the probability of choosing one of the top candidates, given that one of these candidates will accept the offer.
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.