Reinforcement Learning by Policy Search

One objective of artificial intelligence is to model the behavior of an intelligent agent interacting with its environment. The environment's transformations can be modeled as a Markov chain, whose state is partially observable to the agent and affected by its actions; such processes are known as partially observable Markov decision processes (POMDPs). While the environment's dynamics are assumed to obey certain rules, the agent does not know them and must learn. In this dissertation we focus on the agent's adaptation as captured by the reinforcement learning framework. This means learning a policy---a mapping of observations into actions---based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. The set of policies is constrained by the architecture of the agent's controller. POMDPs require a controller to have a memory. We investigate controllers with memory, including controllers with external memory, finite state controllers and distributed controllers for multi-agent systems. For these various controllers we work out the details of the algorithms which learn by ascending the gradient of expected cumulative reinforcement. Building on statistical learning theory and experiment design theory, a policy evaluation algorithm is developed for the case of experience re-use. We address the question of sufficient experience for uniform convergence of policy evaluation and obtain sample complexity bounds for various estimators. Finally, we demonstrate the performance of the proposed algorithms on several domains, the most complex of which is simulated adaptive packet routing in a telecommunication network.

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.

Geometric Structure of the Adaptive Controller of the Human Arm

The objects with which the hand interacts with may significantly change the dynamics of the arm. How does the brain adapt control of arm movements to this new dynamic? We show that adaptation is via composition of a model of the task's dynamics. By exploring generalization capabilities of this adaptation we infer some of the properties of the computational elements with which the brain formed this model: the elements have broad receptive fields and encode the learned dynamics as a map structured in an intrinsic coordinate system closely related to the geometry of the skeletomusculature. The low--level nature of these elements suggests that they may represent asset of primitives with which a movement is represented in the CNS.

An Electronic Market-Maker

This paper presents an adaptive learning model for market-making under the reinforcement learning framework. Reinforcement learning is a learning technique in which agents aim to maximize the long-term accumulated rewards. No knowledge of the market environment, such as the order arrival or price process, is assumed. Instead, the agent learns from real-time market experience and develops explicit market-making strategies, achieving multiple objectives including the maximizing of profits and minimization of the bid-ask spread. The simulation results show initial success in bringing learning techniques to building market-making algorithms.

Scaling algorithms for distributed max flow

Bibliography: p. 22-24.

eCAT-Listening : Design and psychometric properties of a computerized adaptive test on English Listening

Resumen tomado de la publicaci??n

Enhancing fault management performance of two-step QoS routing algorithms in GMPLS networks

In this paper a novel methodology aimed at minimizing the probability of network failure and the failure impact (in terms of QoS degradation) while optimizing the resource consumption is introduced. A detailed study of MPLS recovery techniques and their GMPLS extensions are also presented. In this scenario, some features for reducing the failure impact and offering minimum failure probabilities at the same time are also analyzed. Novel two-step routing algorithms using this methodology are proposed. Results show that these methods offer high protection levels with optimal resource consumption

Enhancing MPLS QoS routing algorithms by using the network protection degree paradigm

IP based networks still do not have the required degree of reliability required by new multimedia services, achieving such reliability will be crucial in the success or failure of the new Internet generation. Most of existing schemes for QoS routing do not take into consideration parameters concerning the quality of the protection, such as packet loss or restoration time. In this paper, we define a new paradigm to develop new protection strategies for building reliable MPLS networks, based on what we have called the network protection degree (NPD). This NPD consists of an a priori evaluation, the failure sensibility degree (FSD), which provides the failure probability and an a posteriori evaluation, the failure impact degree (FID), to determine the impact on the network in case of failure. Having mathematical formulated these components, we point out the most relevant components. Experimental results demonstrate the benefits of the utilization of the NPD, when used to enhance some current QoS routing algorithms to offer a certain degree of protection

Adaptive integral assessment package for the A2UN@ project

This paper presents a first approach of Evaluation Engine Architecture (EEA) as proposal to support adaptive integral assessment, in the context of a virtual learning environment. The goal of our research is design an evaluation engine tool to assist in the whole assessment process within the A2UN@ project, linking that tool with the other key elements of a learning design (learning task, learning resources and learning support). The teachers would define the relation between knowledge, competencies, activities, resources and type of assessment. Providing this relation is possible obtain more accurate estimations of student's knowledge for adaptive evaluations and future recommendations. The process is supported by usage of educational standards and specifications and for an integral user modelling

Designing context-aware adaptive units of learning based on IMS-LD standard

Learning contents adaptation has been a subject of interest in the research area of the adaptive hypermedia systems. Defining which variables and which standards can be considered to model adaptive content delivery processes is one of the main challenges in pedagogical design over e-learning environments. In this paper some specifications, architectures and technologies that can be used in contents adaptation processes considering characteristics of the context are described and a proposal to integrate some of these characteristics in the design of units of learning using adaptation conditions in a structure of IMS-Learning Design (IMS-LD) is presented. The key contribution of this work is the generation of instructional designs considering the context, which can be used in Learning Management Systems (LMSs) and diverse mobile devices

Adaptive intelligent agent approach to guide the web navigation on the PLAN-G distance learning platform

Hypermedia systems based on the Web for open distance education are becoming increasingly popular as tools for user-driven access learning information. Adaptive hypermedia is a new direction in research within the area of user-adaptive systems, to increase its functionality by making it personalized [Eklu 961. This paper sketches a general agents architecture to include navigational adaptability and user-friendly processes which would guide and accompany the student during hislher learning on the PLAN-G hypermedia system (New Generation Telematics Platform to Support Open and Distance Learning), with the aid of computer networks and specifically WWW technology [Marz 98-1] [Marz 98-2]. The PLAN-G actual prototype is successfully used with some informatics courses (the current version has no agents yet). The propased multi-agent system, contains two different types of adaptive autonomous software agents: Personal Digital Agents {Interface), to interacl directly with the student when necessary; and Information Agents (Intermediaries), to filtrate and discover information to learn and to adapt navigation space to a specific student

Improving Clustering Algorithms for Image Segmentation using Contour and Region Information

In image segmentation, clustering algorithms are very popular because they are intuitive and, some of them, easy to implement. For instance, the k-means is one of the most used in the literature, and many authors successfully compare their new proposal with the results achieved by the k-means. However, it is well known that clustering image segmentation has many problems. For instance, the number of regions of the image has to be known a priori, as well as different initial seed placement (initial clusters) could produce different segmentation results. Most of these algorithms could be slightly improved by considering the coordinates of the image as features in the clustering process (to take spatial region information into account). In this paper we propose a significant improvement of clustering algorithms for image segmentation. The method is qualitatively and quantitative evaluated over a set of synthetic and real images, and compared with classical clustering approaches. Results demonstrate the validity of this new approach

Adaptive business intelligence for an open negotiation environment

Engineering of negotiation model allows to develop effective heuristic for business intelligence. Digital ecosystems demand open negotiation models. To define in advance effective heuristics is not compliant with the requirement of openness. The new challenge is to develop business intelligence in advance exploiting an adaptive approach. The idea is to learn business strategy once new negotiation model rise in the e-market arena. In this paper we present how recommendation technology may be deployed in an open negotiation environment where the interaction protocol models are not known in advance. The solution we propose is delivered as part of the ONE Platform, open source software that implements a fully distributed open environment for business negotiation

An analysis of trust in anonymity networks in the presence of adaptive attackers

Introduces extended Crowds protocols. Optional reading