On the Convergence of Stochastic Iterative Dynamic Programming Algorithms

Recent developments in the area of reinforcement learning have yielded a number of new algorithms for the prediction and control of Markovian environments. These algorithms, including the TD(lambda) algorithm of Sutton (1988) and the Q-learning algorithm of Watkins (1989), can be motivated heuristically as approximations to dynamic programming (DP). In this paper we provide a rigorous proof of convergence of these DP-based learning algorithms by relating them to the powerful techniques of stochastic approximation theory via a new convergence theorem. The theorem establishes a general class of convergent algorithms to which both TD(lambda) and Q-learning belong.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Reasoning about Temporal Context using Ontology and Abductive Constraint Logic Programming

The underlying assumptions for interpreting the meaning of data often change over time, which further complicates the problem of semantic heterogeneities among autonomous data sources. As an extension to the COntext INterchange (COIN) framework, this paper introduces the notion of temporal context as a formalization of the problem. We represent temporal context as a multi-valued method in F-Logic; however, only one value is valid at any point in time, the determination of which is constrained by temporal relations. This representation is then mapped to an abductive constraint logic programming framework with temporal relations being treated as constraints. A mediation engine that implements the framework automatically detects and reconciles semantic differences at different times. We articulate that this extended COIN framework is suitable for reasoning on the Semantic Web.

Preconditioning and iterative solution of symmetric indefinite linear systems arising from interior point methods for linear programming

We study the preconditioning of symmetric indefinite linear systems of equations that arise in interior point solution of linear optimization problems. The preconditioning method that we study exploits the block structure of the augmented matrix to design a similar block structure preconditioner to improve the spectral properties of the resulting preconditioned matrix so as to improve the convergence rate of the iterative solution of the system. We also propose a two-phase algorithm that takes advantage of the spectral properties of the transformed matrix to solve for the Newton directions in the interior-point method. Numerical experiments have been performed on some LP test problems in the NETLIB suite to demonstrate the potential of the preconditioning method discussed.

Behavioral Measures and their Correlation with IPM Iteration Counts on Semi-Definite Programming Problems

We study four measures of problem instance behavior that might account for the observed differences in interior-point method (IPM) iterations when these methods are used to solve semidefinite programming (SDP) problem instances: (i) an aggregate geometry measure related to the primal and dual feasible regions (aspect ratios) and norms of the optimal solutions, (ii) the (Renegar-) condition measure C(d) of the data instance, (iii) a measure of the near-absence of strict complementarity of the optimal solution, and (iv) the level of degeneracy of the optimal solution. We compute these measures for the SDPLIB suite problem instances and measure the correlation between these measures and IPM iteration counts (solved using the software SDPT3) when the measures have finite values. Our conclusions are roughly as follows: the aggregate geometry measure is highly correlated with IPM iterations (CORR = 0.896), and is a very good predictor of IPM iterations, particularly for problem instances with solutions of small norm and aspect ratio. The condition measure C(d) is also correlated with IPM iterations, but less so than the aggregate geometry measure (CORR = 0.630). The near-absence of strict complementarity is weakly correlated with IPM iterations (CORR = 0.423). The level of degeneracy of the optimal solution is essentially uncorrelated with IPM iterations.

Operational Cost Reduction in WDM Networks using Lighttours

Wavelength division multiplexing (WDM) networks have been adopted as a near-future solution for the broadband Internet. In previous work we proposed a new architecture, named enhanced grooming (G+), that extends the capabilities of traditional optical routes (lightpaths). In this paper, we compare the operational expenditures incurred by routing a set of demands using lightpaths with that of lighttours. The comparison is done by solving an integer linear programming (ILP) problem based on a path formulation. Results show that, under the assumption of single-hop routing, almost 15% of the operational cost can be reduced with our architecture. In multi-hop routing the operation cost is reduced in 7.1% and at the same time the ratio of operational cost to number of optical-electro-optical conversions is reduced for our architecture. This means that ISPs could provide the same satisfaction in terms of delay to the end-user with a lower investment in the network architecture

G+: Enhanced Traffic Grooming in WDM Mesh Networks using Lighttours

In this article, a new technique for grooming low-speed traffic demands into high-speed optical routes is proposed. This enhancement allows a transparent wavelength-routing switch (WRS) to aggregate traffic en route over existing optical routes without incurring expensive optical-electrical-optical (OEO) conversions. This implies that: a) an optical route may be considered as having more than one ingress node (all inline) and, b) traffic demands can partially use optical routes to reach their destination. The proposed optical routes are named "lighttours" since the traffic originating from different sources can be forwarded together in a single optical route, i.e., as taking a "tour" over different sources towards the same destination. The possibility of creating lighttours is the consequence of a novel WRS architecture proposed in this article, named "enhanced grooming" (G+). The ability to groom more traffic in the middle of a lighttour is achieved with the support of a simple optical device named lambda-monitor (previously introduced in the RingO project). In this article, we present the new WRS architecture and its advantages. To compare the advantages of lighttours with respect to classical lightpaths, an integer linear programming (ILP) model is proposed for the well-known multilayer problem: traffic grooming, routing and wavelength assignment The ILP model may be used for several objectives. However, this article focuses on two objectives: maximizing the network throughput, and minimizing the number of optical-electro-optical conversions used. Experiments show that G+ can route all the traffic using only half of the total OEO conversions needed by classical grooming. An heuristic is also proposed, aiming at achieving near optimal results in polynomial time

A mixed H2/H∞-based semiactive control for vibration mitigation in flexible structures

In this paper, we address this problem through the design of a semiactive controller based on the mixed H2/H∞ control theory. The vibrations caused by the seismic motions are mitigated by a semiactive damper installed in the bottom of the structure. It is meant by semiactive damper, a device that absorbs but cannot inject energy into the system. Sufficient conditions for the design of a desired control are given in terms of linear matrix inequalities (LMIs). A controller that guarantees asymptotic stability and a mixed H2/H∞ performance is then developed. An algorithm is proposed to handle the semiactive nature of the actuator. The performance of the controller is experimentally evaluated in a real-time hybrid testing facility that consists of a physical specimen (a small-scale magnetorheological damper) and a numerical model (a large-scale three-story building)

Introduction to JavaScript Programming

These are the resources for an introductory lecture in JavaScript programming. Exercises are provided to practice simple JavaScript programming, including a template for a DHTML implementation of Conway's Game of Life (with encrypted solution).

Mathematical Programming

Exam questions and solutions for a third year mathematical programming course.

Programming & Software

An overview of programming and software development.

Programming Principles: Starting Out

In this lecture we describe the structure of the Programming Principles course at Southampton, look at the definitions and paradigms of programming, and take a look ahead to the key things that we will be covering in the weeks ahead.

Programming Principles: Introduction to Java

In this lecture we look at key concepts in Java: how to write, compile and run Java programs, define a simple class, create a main method, and use if/else structures to define behaviour.