CETINIA Publications

CETINIA's main objective is generating, applying and promoting knowledge in the area of Intelligent Information Technology, as well as consolidating the visibility and the academic prestige of the University Rey Juan Carlos, both nationally and internationally. For this reason, CETINIA started a series of publications to disseminate the scientific results achieved by the members of the centre. These publications are intended to collect doctoral thesis as well as collections of scientific papers.

Coordination Mechanisms for Agent-based Smart Grids

In Abril 2014 the book Coordination Mechanisms for Agent-Based Smart Grids, by Dr. Radu-Casian Mihailescu, was published in the CETINIA series. This book introduces a multiagent approach for modelling the emerging complexity of the energy industry. While the traditionally centralized management of the system becomes less viable in the context of distributed generation and controllable loads, the underlying thread of this work advocates the design and implementation of coordination mechanisms capable to integrate and manage a large-scale integration of such devices via agent-based control. We begin by proposing mechanisms for micro-grid formation and enhance their operation along two aspects: on the hand (supply-side) we are concerned with seamlessly integrating distributed generation to ensure a reliable service of energy supply comparable to what a large power plant delivers today. We first address the economic benefits of virtual power plants in a game-like setting and then go on to propose a DCOP-based formalism for solving the schedule generation problem, while accounting for the stochastic behaviour of intermittent supply. On the other hand (consumer-side), we apply the use of game mechanics to drive the behaviour of prosumers towards efficient grid-wise use of energy. Finally, we propose a collusion detection mechanism that complements the above-mentioned solutions in the sense of inspecting for patterns where agents tacitly cooperate through illicit monopoly tactics to manipulate energy markets.

Gaming with Emotions: An Architecture for the Development of Mood-Driven Characters in Video Games

In September 2013 the book Gaming with Emotions, by Dr. Luís Peña Sánchez, was published in the CETINIA series. The book studies the emotional component of the behavior of artificial characters in video games. The author develops an emotion simulation model called EEP that accounts for the impact of external events on a character’s mood state, and analyzes its relevance for the development of mood-driven behaviors as part of the control strategies of artificial characters. In addition, he provides a mechanism that improves the development procedure of video game characters, by developing a new hybrid machine learning model called WEREWoLF that purposefully combines reinforcement learning and evolutionary techniques, so as to automatically generate character control strategies associated to different mood states. Both models are integrated into the AGCBAR architecture, that supports the efficient design of mood-driven strategies for artificial characters in video games. The adequacy of the above architecture and its components is first assessed seperately through individual experiments. Then, the author implements the complete architecture together with an experimental video game framework in a complex case study, comparing the development effort of mood-driven artificial characters using the AGCBAR architecture together with EEP and WEREWoLF, to traditional implementation techniques.

Sequential Decision Making in Normative Environments

On November 2012, the book Sequential Decision Making in Normative Environments, by Dr. Moser Silva Fagundes, has been published. This book collects CETINIA's advances in normative multiagent systems. A broad variety of norm-aware agent models and architectures have been developed, aimed at implementing the normative reasoning of agents with different levels of autonomy and in different types of environments. However, approaches that allow autonomous agents to generate complex plans in dynamic and non-deterministic normative environments are rare. This book introduces the Normative Markov Decision Processes (NMDPs), an extension of the Markov Decision Processes (MDPs) for modeling norm-aware rational agents acting in normative stochastic environments, as well as two utilitarian models of normative reasoning, pertaining to self-interested and norm-compliant agents. While the self-interested agents prioritize the maximisation of utilities over the compliance with norms, the norm-compliant agents prioritise the norm-abiding behavior over the utility maximisation. Several experiments were performed in a simulated motion environment, measuring the performance of different populations of agents in relation to specific controlled settings.

From Belief to Knowledge

On November 2012, the book From Belief to Knowledge, by Dr. Levan Uridia, has been published. This book collects CETINIA's efforts to combine belief and knowledge into one formalism, a problematic issue in epistemology. One of the central standing questions in philosophy is to define knowledge in an universal way. One of the central ideas is that knowledge and belief can be understood as relations between a cognitive agent a and a proposition p. The book presents a new modal logic based formalism, called doxepi-formalism, that on the basis of a known epistemic logic LE finds a good doxastic logic L which combines with LE in a sufficient way. In the book this task is accomplished for the logics S5 and S4 and several different concepts and doxepi-formalisms based on these logics are studied.

Incentive Mechanisms for the Regulation of Open Multiagent Systems

On November 2012, the book Mecanismos incentivos para la regulación de sistemas multiagente abiertos basados en organizaciones (Incentive Mechanisms for the Regulation of Open Multiagent Systems), by Dr. Roberto Centeno, has been published. This book collects the results obtained at CETINIA in the field of incentive mechanisms to influence the behaviour of a population of agents. The common solution adopted for regulating this kind of systems is based on organisational concepts. In most of the proposed models, normative systems appear as a key concept. Due to the nature of open systems, the task of defining effective sanctions for an unknown and heterogeneous population becomes complex and difficult. Facing this problem, the author proposes an incentive mechanism able of learning effective sanctions, at runtime, adapting them to the individuals, as well as to the particular situation of the system.

The concept of trust in organisational systems. A coordination approach for software agents

On Abril 2011, the book El concepto de confianza en sistemas organizativos (The concept of trust in organisational systems. A coordination approach for software agents), by Dr. Ramón Hermoso, has been published. This book collects the results obtained at CETINIA in the field of trust and reputation in open multi-agent systems. Trust models are generally used in computational systems to infer expectations about future behaviour of other entities that populate the system by using information based on past experiences. These models are particularly relevant when agents have to decide which other individuals to interact with, in order to perform a certain action. This work tackles this issue by making use of organizational structures. It also provides the design and validation of a mechanism that allows the evolution of those organizational structures in open multi-agent systems.

Service Description, Matchmaking and Composition in Open Multi-Agent Environments. An Organisational Approach

On December 2010, the book Descripción, Descubrimiento y Composición de Servicios en Entornos Multiagente Abiertos. Un Enfoque Organizacional (Service Description, Matchmaking and Composition in Open Multi-Agent Environments. An Organisational Approach), by Dr. Alberto Fernández, has been published. This book collects the results obtained at CETINIA in the field of service description, discovery and composition in open multi-agent environments, where agents are able to engage in different types of social interactions during service provision. A new approach is proposed, which extends current trends to semantic service description, matchmaking and composition is MAS by using organisational concepts, such as roles and interactions. A matchmaking algorithm that uses those semantic descriptions is described. Furthermore, it is presented a generic method that exploits the MAS organisational information in order to heuristically filter out those services that are probably irrelevant to the planning process. The empirical evaluation of the proposed methods allowed us to test their validity. Finally, examples of application of those proposals in the fields of transportation management and medical emergency service coordination are shown.

Vehicle-centric coordination for urban road traffic management. A market-based multiagent approach

On December 2009, the book Vehicle-centric coordination for urban road traffic management. A market-based multiagent approach, by Dr. Matteo Vasirani, has been published. This book collects the most recent results obtained at CETINIA in the field of Intelligent Transportation Systems. The book explores the application of resource allocation techniques, based on artificial agent-based markets, to the urban traffic domain. These techniques span from combinatorial auctions for the allocation of slots at intersections, to traffic assignment mechanisms inspired by the general market equilibrium theory to achieve a better distribution of traffic in a road network. The experimental results collected in this book showed how the automation of the traffic infrastructure, as well as a tighter integration with the vehicles, has a great potential to improve the efficiency of a urban road traffic system.