Miguel Rebollo

Detrás de este título tan atractivo y motivador se enconde un post… acorde con el título :-) Básicamente la idea es tener algo que nos sirva como ejemplo para empezar a estudiar los espacios de acuerdos y su dinamica en un problema más “Consolider”. Y el ejemplo elegido es el modelado de una red fluvial. El propósito es poder usar los modelos de redes de consenso para tratar de modelar las interacciones en un sistema multiagente (SMA) para alcanzar un acuerdo. A través de los espacios de acuerdo puede llegarse a un conjunto de restricciones unidas a las leyes que regulan la propia dinámica del río. Y con algoritmos bien conocidos para resolver problemas de consenso en redes, a partir de su matriz Laplaciana

,

donde mantiene el grado de los nodos de la red y se define como

si y si

Para poder aplicarlo, es necesario disponer de un modelo de una red fluvial sobre el que se pueda aplicar este formalismo. El modelo de Scheidegger (1967) define la red como un grafo dirigido aleatorio sobre un retículo triangular. En cada intersección, se escoge al azar entre las dos posibles ramificaciones (izquierda o derecha). De esta manera, cada rama del rio es capaz de drenar una superficie de , donde es la distancia entre dos vecinos (es decir, que las distancias entre cada segmento de río es de -por simplicidad se suele escoger la unidad-).

Por otra parte, para determinar la relación entre el área de drenaje de un río y la longitud de su flujo principal se emplea la Ley de Hawk (1957):

donde l es la longitud del flujo principal, a es el área y el exponente de Hack h se calcula empíricamente y se encuentra en el rango 0.5-0.7. Con estos parámetros, es posible generar aleatoriamente redes que modelan un rio de forma realista, con lo que es posible generar distintos casos de prueba y comprobar empíricamente la validez de las propuestas.

Sobre estos modelos de rios, habrá que distribuir una red de agentes que representen las distintas entidades y personas responsables de la gestión y del consumo de los recursos hídricos. Creo que lo más adecuado es modelarlo como una red de tipo small world que simule las relaciones existentes entre los participantes. de esta forma es posible modelar las relaciones cercanas (entre regantes de una misma comarca) pero también la existencia de posibles relaciones lejanas que podrían modelar incluso a regantes de otras cuencas. Pero esta parte de la red social de riego la dejo para otra anotación

Para más información…

Dodds, Peter Sheridan: Geometry of river networks.- Thesis (Ph.D.)–Massachusetts Institute of Technology, Dept. of Mathematics, 1969. (PDF)

Referencias

J. T. Hack. Studies of longitudinal stream profiles in Virginia and Maryland. In U.S.Geol. Surv.Prof. Pap., 294-B:45–97, 1957.

A. E. Scheidegger. A stochastic model for drainage patterns into an intramontane trench. In Bull. Int. Assoc. Sci. Hydrol., 12(1):15–20, 1967.

Enforcing Security in the AgentScape Middleware
AgentScape is a middlewareto create agent-based applications and in this paper they’re showing how threads can be managed by using the security architecture for AgentScape. He begins with the architecture (see in AgentScape web wite).Two basic problemas: malicious hosts and malicious agents. SO basic sec. requirements are (i) authentification, (ii) integrity-migration- and (iii) authorisation.

Developing Intelligent Agents in Android Platform
Well, this is mine, so I’ll write it later :-)

Magentix: a Multiagent Platform Integrated in Linux
I know that, so I haven’t a lot of things to say. Magentix is an agent platform that are focus en scalability and efficiency, so it is quite integrated with the operative systems instead of using middleware (what will get him into trouble in a moment ;-). AMS (white pages) and DF (yellow pages) are distributed in different hosts and all that information is replicated (I hate that). Something interesting is how organisations are managed by the platform by the Organisational Unit Manager (OUM).

Only a question… what’s new on that? It sounds to me a lot!

From the assistants: about the RDF codification of messages (performance); problems: interoperability, integration with other tools, and AN ENVIRONMENT FOR PROGRAMMING DIFFERENT THAT VI!!!! ; other about scalability with AMS distribution in large systems (I said it!). And the last one, why comparing only with JADE.

Tags: eumas, agent, tools, agentspace., magentix, android, mda, mdd, pim, psm, jade-leap

An Agent Based System for Distributed Information Management: A Case Study
Sorry, I’m late :-(

Scholar Agent Alpha
Auction mechanism for authors (they pay for having their paper published). WHen they win the auction then they can use their “rights” to publish the paper. They are using a vickery auction (second price, closed envelope). the process is the following

1. call for papers
2. authors register themselves
3. authors bids (once)
4. system reports to winners and loser
5. wining paper is submitted for publication (and paid)

More cycles can be done, so agents can modify their bids and try to win.

Conservative Re-Use Ensuring Matches for Service Selection
Automatic retrieval, a semantic is needed (OWL-S, WSMO) and IOPEs has to be annotated. And flexible matches are very important (services that do not exactly match). But current semantic matchmaking considers services as a single operation. She proposes for the services to have roles inside a composed service. But for many of the operations are offered by patterns that are still unkown. And context usually is not taken into account, so the global goal can not be preserved, so they define an action-based representation of the operations of a service and an extension of re-use ensuring matches to produce substitutions that preserve goals. A modal logic is used; states are fluents and there’re 4 types of operations: one-way, notification, request-response and solicit-response. With those elements, choreography is defined through roles and all complex services will still works if conservative substitution is guaranteed. ANd this can be done if casual chains of actions are not broken when actions are sbustituted. What is important is that the problem of determining if a substitution is conservative is decidible.

A big “but”: youi need to have a choreography. Services can not discover service compositions, but working over a composite service and look for suitable substitutions.

Evolving Ontological Knowledge Bases through Agent Collaboration
Problem: an agent gives a queary about a concept c that it is not known, so the question can not be answered. Option 1: consult a mediator. Option 2: consult other agents. After that, some fragment of the ontology can be requested so the original agent can augment its knowledge and perform better interactions. But it has a cost and may not benefit the agent (it do not weigh the cost) ==> evolutionary method to augment ontologies with concepts related to its intereset domain. Two steps:

1. Merge Fragments: check which ones are related and merge them into one, create a powerset of all the axioms and, for each memmber of the powerset, check the consistence with existing ontology
2. Selection Process: find the average depth of the fragment, select the related properties level by level and incorporate them to the ontology.

This has been checked with an small number of agents (5 query and 10 speciliased) and several benchmarks. But htere’s no method for measuring the complexity of a T-Box.

Very interesting. One of the best papers I’ve seen these days.

Tags: eumas, agents, information, services, ontologies, owl-s, iope

Norms for Agent Service Controlling
About how add a normative system in an open system where agents and web services co-exist and interact. Agents are grouped in organisational units (OU), as coallitions or teams. OU provides services to the agents (or even the designers) to manage the organisation. They’re classified into 3 types: structrural (norm, role and unit creation), informational (about the current state) and dynamic (role adquisition).

Norms regulate the organisation and they’re divided into organisational and functional norms. She shows with an example the different type of norms, services and how all that works.

One thing that I don’t like is the definition of a new language. There’s well known logic specification and standards to formalise these concepts. A new language nowadays just complicate the interaction, even more for open systems…. and Pablo Noriega thinks as me :-)

Towards the Group FormationRecognition through Social Norms
Social norms are a good complement to laws, based on coordinated reaction on the members of the group. A norm is a set of observables and one action. How agent recognise as members of the same group? (that is, they have the same set of rules) They follow 4 algorithms: (i) basic (interact and save) (ii) the friends of my friends are also my friends (whitelist), (iii) blacklist (the opposite one) and (iv) labelling. Labels are put on the agents when they interact. They’re public: all agents can see them, but one agent can remove its own labels. False positives behave similar in the case of white and black lists. And it works better (obviously) for heterogeneous groups than for homogeneous groups. Very interesting. Take a closer look to that.

Integrating Image and Reputation Information in BDI Agents
3 approaches to control interactions among agents are possible: security, institutional and social (reputatin based). The last one can be modelled in a centralised way (as eBay) or decentrlised way (more interesting) and he’s going to present the Repage system to model image and reputation, integrated into a BDI agent. The difference between them is that image is my own view of the agent (experience-based), whereas reputation is what other agents say. A recommended lecture: the paper with six definitions for trust (look for it)

An Extendedc. Using Institutions To Foster Compliance in Open Multi-Agent Systems
Problem in open systems: heterogenous agents, with conflicting individual goals and limited trust. Some uncertainties (parametric -> environmental) can’t be reduced, but strategic ones can (decide if one agent has a bad behaviuour deliverately). In the case of anoinymous communities with esporadic interaction, it is very difficult to get efficient exchanges in the long run. But this can be solve even without superior detection capabilities by extending it. Well, she’s changing a bit the game because she adds a new player, but it is no serious.

Tags: eumas, agents, services, norms, organisation, institution

From Agents to Artifacts Back and Forth
In MAS, environment is considered as a monolithic and centralised component. This paper proposes a model based on artifacts. An artifact has (i) an user interface that provide operations for using it, (ii) the observable state, (iii) a mechanism to signal to external artifacts and (iv) a link interface to link to other artifacts.

But artifacts are not agents, they only react, they’re passive. And they are not objects either. A sample is shown in Cartago architcture. From the agent viewpoint, artifacts embedded operational and epistemic functions.

Towards Agent-Oriented Model Driven Engineering
To create MAS is a complex activity and many methodologies integrate MDE principles. MDE is based in the concept of model. They’re talking abut how differente methodologies, such as Ingenias or Adelfe are using MDE concepts. Some considerations: (i) concepts are still evolving, (ii) own semantic concepts, (iii) a wide range of levels of abstraction. They propose Model transformation By Example (MTBE), creating automatic transformation between pairs of models and shows some examples about how it works. The idea is to provide the tools with pairs of models that correspond to a transformation, so the systmen could learn from the and apply it to other cases. An very intersenting open issue-future work is how to include negative examples.

Reducing Communication Cost Via Overhearing
Showing how to reduce the communnoication cost by using mediators that filter invalid illocutions. The cost depends on the bandwith of the communication channel and the ammount of CPU (processing time) used to detect invalid illocutions. Interesting… and some ideas that I can use for SF distribution.

Towards Organizational Agent-Oriented Operating Systems
(Confirmado… Pixel sabe leer :-) Agent are complex systems but agents and even their platforms have no help from the operative system (OS), so they (we) are trying to define-and meybe to create-an OS that incorporate more complex abstractions to facilitate the execution of the agents.

Instead of being the process the basic exectional entity, agents organisations are included into the OS. Its based on a client-server view (I don’t like it), where there’re agents that provide services and others than ask from them. Services can be classified into two types: operations and resources. Operation serv. are sw services executed by an agent (open) and Resource serv. are hw services provided by devices.

What’s the difference between this proposal and middleware? I guess that it complicates a lot the OS design without giving clear advantages. I think that is better to provide basic management for agent concepts (as communication, roles, norms, organisations and so on), but we don’t need to have agents inside the operative systems.

Tags: agent, developtment, mdd, mda, communication, cartago, ingenias, adelfe

This evening begins with a panel session in which Marco Colombetti, Pavlos Moraitis, Pablo Noriega, Axel Polleres and Carles Sierra will talk about Agreement Technologies (AT).

AT is a paradigm for next-generation open distributen systems, based on the concept of agreement between computational agents. AT has a ‘cake’ (just as web services technology), that establishes the technologies needed for create such systems: semantics, norms, organisations, argumentation&negotiation and trust. All this activities are integrated in a COST action about Agreement Technologies (#IC0801). More information on the AT COST action web site. This initiative is very closely related with the Agreement Technologies group.

Semantics
Semantic aligment is an important issue in open environemnts, where agents meets and interact freeley. The main goals of this groups are

1. integration of ointologies with non-monotionic rules
2. quering over distributed ontologies
3. aligment with existing semantic web standards, enriching them with methods to enforce policies and trust online.

Norms
Reasoning about norms in MAS at design time and run-time to adopt, comply, enforce and modify normative systems. The three main challenges are

1. how to define formal, non-ambiguus and machine understandable nomrs
2. normative reasoning and negotiated  flexibility
3. usability of norms

Organisations
There’re meny interesting common points between organisations and agreements: an agreement is made in the context of an organisation, but meny times an organisation itself is the result of an agreement. Its main challenges are

1. how to model organisations
2. how agreements can be achieved in an organisational context
3. teamwork (team creation, build collective plans, corrdination or dissolution)
4. organisational change
5. implementation (architecture, patterns, environments&tools or verification)

Argumentation & Negotiation
There’s a lot of work done, but the interesting point is how aditional information is provided to the agents to try to convince them with adequate arguments. This way can facilitate the achievement of agreements. Pending issues are

1. the notion of concession is not modelled
2. how agents choose the and offer to propose in each dialogue step
3. deeper investigatiom on the notion of tactics and strategies
4. decision-making models to reach satisfactory agreements

Trust
It is very important after the agreement has been achieved, when agents decide to honour the agreement or not. The idea is focus on groups working on semantics, norms and social models to model trust. Important things to think about are

1. scalability (social network models, large scale systems, negotiation)
2. semantics (not defining a single global ontology, but deal with misbehaviours and misundestandings)
3. similarity (how to use past experiencies to assest how much ‘trust’ you can put non an agreement)
4. balence between norms and trust (the more norms you have, the less risk the opponent has and the less trust measures has to be taken)

After the exposition, some conclusions and questions.

Tags: agreement, agents, semantic, norms, organisation, argumentation, negotiation, trust

Programming Social Processes with Action Languages
A social process is a joint of activities (business, poitical, administrative and so on) performed in a social context. It can be a computational society when a :SocialMiddleware is provided and it can be programmed as a first-class social connector (:SocialInteraction). The abstract machine for the SOcialMiddleware they use action languages (C+): a declarative language to specify structure and dynamics, based upon a propositional, non-monotonic, causal logic, and Ccalc tool (SAT solver).

The social middleware is defined through a set of sorts, objects, fluents, actions, variables and axioms. But to reduce the complexity of these specifications they make a sort-oriented specification. He explains using a tennis match example how the society can be modelled.

WIth all that, a programming language for agent societies can be defined (SPEECH: a societal programming language – www.speechlang.org).

Representing and Reasoning about Norm-Governed Organisations with Semantic Web Languages
SW languages are more limited, but they offer a stardard language (open), advantadges in reasoning (decidability and optimized reasoners). They want to capture roles and role classification, institutionalised powers, normative systems, violations and temporal relationships (hey…. just as I want!!! I have to read it carefully). OWL and SWRL extended for temporal relations (SWRLTab editor) for before, after and during (–> converted into PDDL).

They define permissions, abbligations and permision for roles and inheritance of norms. You can override them if you need more especific norms. There’re general rules form norms (ex. if an act is permitted then it’s not prohibited / if an act is obligatory the it’s permitted… ) Other cocept modelled is “power” (a role has the powerto execute an action). Norms can have conditions and deadlines, but the DL reasoner has to be extended to del with temporal relationships (this can be an interesting work to do) To detect violations, the system can check if an agent triesto perform an act that is prohibited. That can be detected automatically by the reasoner.

But we can reason an inconsistent ontology by tolerating contradictions (that’s interesting for open systems or self-organising systems)

Limitations (comparing with event calc.): only binary operators, static knowledge, no modifications

On Partial Deductions and Conversational Agents
Many times, human conversations include more information that a simple yes/no answer, so if agents want to interact with human complex conversation schemes have to be included in their mental state.

The mental state of an agent is formed by a ….., a …. and a set of rules. Goals are facts that agents want to be solve. THe input and the output interface are set of facts. Agents communicate using an own simple speech act messages. Interface engine os based on rle specialisation uses an approximate reasoning context and the true value is not binary, but a fuzzy one.

Examples to show the mentak state cycle and hoe agents communicates to complete their information.

Tags: eumas, programming, reasoning, semantic web, owl, swrl, swrltab

Coallition Structure Generation: Dynamic Programming Meets Anytime Optimization
Just how to optimize coallition formation based on its utility. Nothing new, but the method used: an anytime algorithm (IP). He’s comparing with a previos work based on dynamic programming (IDP). The proposal is to divide the search space in subspaces and to add an upper and a lower bound. The subspaces are made by the number of agents in eachs group (f.i. [1,3] means all coallitions formed by one isolated agent and a group of 3). He adjust the behaviour of the algorithm between being IP or IDP. Good results…. but for 23 agents only!! Let’s try with 100. This solution is O(n^n).

Only a question: they’ve published a paper (about IDP)  with worse results than a previous one (IP) And they’re only comparing with themselves. I can’t do that, reviwers don’t allow me to do that.

Optimal Coalition Structure Generation In Partition Function Games
A question: what happen if the value of a coallition depends on the value of the rest of the coallitions? (that is: the partition function). There’re many example of real systems working in that way; economics (petrol, R&D coallitions or coordination of monjetary policies) and other areas.

Patterns:

• positive externalities: when one coallition is formed all the rest increase their value
• nevative externalities: when one coalition is formed all the rest decrease its value
• super-additive: when one coallition is formed it increases its value
• sub-additive: when one coallition is formed it decreases its value

and he consideres its combinations. He explains the algorithms used to create the coallitions, usgin the same algorithm that in the previous speech (anytime).

A problem with all that: how the utility is calculated for coallitions? I have no faith in utility.

From Agent Games Protocols to Implementable Roles
Problems:service composition at run-time. He shows an example about merchant delivery, and shows that protocols can content errors, that can be solve by taking into account roles to deal with invisible transitions. Ups, that’s the end and I haven’t the point :-( I have no idea what he is talking about.

Adaptation in a P2P Scenario with 2-LAMA
Jordi explains that MAS organization can be adapted by using a layer of specialised agents in charge of supervise the systen. Itis applied in a P2P environment. The organisation is formed by a set of roles, protocols and norms. Agents are organised in two levels: Domain-level (DL) and Meta-level (ML).

Tos test it, they’ve used a modified (simplifies) version of BitTorrent protocol. Domain-level agents are organised in clusters and each cluster is supervised by an assistant in a Meta-level. Experiments have been organised in 3 arqchitectures: All4all, centralised and distributed. Good enogh results.

What’s the difference with P4P? I’ll look for it.

Tags: eumas.coallition, coordination

Natalia nos va a contar cosas sobre agentes y normas.

La base lógica de las normas son lógicas deónticas, que permite abordar conceptos normativos: básicamente obligaciones, permisos y prohibiciones.

Los SMA normativos aparecen de la intersección de SMA con sistemas normativos que vienen de teorías legales. En primer lugar, debe definirse un modelo normativo, a partir del cual se definen los estados por los que pueden pasar las normas y las relaciones que existen entre distintas normas.

Una de las propuestas más recientes son la metáfora de agente: ver el sistema como un agente que tiene como objetivo el definir y vigilar el cumplimiento de las normas.

Basado en estos sistemas, se detecta la necesidad de definir un lenguaje normativo, que debe ser suficientemente general para representar los mecanismos básicos y lo suficientemente concreto para que sea ejecutable.

Cuestiones abiertas:

1. desarrollo de un lenguaje computacional para especificar sistemas normativos
2. razonamiento normativo individual (incorporar razonamiento sobre normas)
3. herramientas para la implementación de SMA normativos

Ahora empieza lo interesante: uso en una arquitectura para sistemas multiagente abiertos a gran escala para el modelado de organizaciones virtuales. Se basa en SOA.

Las normas definen los 3 conceptos deónticos básicos, extendidos con restricciones temporales (basadas en intervalos -before, after….-) y con la posibilidad de definir sanciones y recompensas.

Las normas están clasificadas en dos grandes grupos:

1. normas organizacionales, relacionadas con los servicios ofrecidos por la arquitectura (p. ej., cardinalidad)
2. normas funcionales, definidas dentro el dominio de aplicación y soportadas por los agentes.

Disponemos de un sistema que permite traducir las normas a sintaxis BFN y se inserta en una base de hechos (utilizando Jess como motor de razonamiento). Aunque ha comentado que las reglas tienen dos partes (LHS y RHS), realmente tienen 3 (evento, condición, acción) e incluso cuatro (añadiendo una sanción/recompensa).

Con esto (muy resumido) se ofrece un lenguaje normativo para regular organizaciones virtuales, centrada en el acceso a servicios. Os dejaré una referencia para que os enteréis con más detalle de qué va.

El problema que le veo es que la base formal es un poco débil. Para la inclusión de los servicios y de restricciones temporales habría que usar directamente mecanismos más complejos, basados en lógicas modales o lógicas de acción, que ofrecen las abstracciones necesarias para razonar ton los conceptos deónticos, con los servicios (modelados con acciones) y con restricciones temporales. Particularmente, creo que con TLA (Temporal Logic of Actions -PDF-) podríamos hacer casi todo lo que necesitamos, incluyendo además de las normas la gestión de servicios con un único formalismo y también un lenguaje único, que facilitaría los desarrollos.

En el workshop WAT 09, que se celebra hoy en Lisboa. (explicar un poco dequé va)

Modelling Agreement Spaces. Este es mío y de Carlos. Básicamente se trata de definir el contexto en el que se va a desempeñar el agreement. Para eso, se propone una visión geométrica del problema, como en espacio de contextos n-dimensional donde cada dimensión es un concepto compartido entre las entidades. Las restricciones que cada entidad impone al acuerdo son planos (hiperplanos) y su intersección definen la porción de espacio en la que se ejecutará el acuerdo. Si el espacio es convexo, podemos asegurar que cualquier ‘movimiento’ dentro del espacio siempre está dentro del acuerdo. Se usa un CSP para construir deforma incremental el espacio de acuerdos que garantiza que el espacio que se construye siempre es contexto y por lo tanto siempre tendrá solución. SI no la hay, un intermediario puede relajar las restricciones para conseguir un espacio convexo.

Towards a Conceptual Framework for Organizational Mechanisms in Multiagent Systems. Es el turno de Roberto. Después de definir su visión de agente, pasa a hablar de la parte interesante: un sistema multiagente organizacional. Tiene 2 puntos de vista: uno micro (agentes individuales) y otro macro (del sistema completo). Y para ambos el sistema organizaciones muestra 2 perspectivas: la informativa y la regulativa. La diferencia es que las segundas producen cambios en el entorno y las primeras no (tienen que ver con intercambio de conocimiento). Además los agentes no pueden decidir usar o no mecanismos de regulación (se imponen). La pega es que es un sistema basado en utilidad, una función extremadamente difícil de definir ¿cómo definir en un número el provecho que puedo sacar de realizar  o no una determinada acción? Un ejemplo de un mecanismo organizacional es el rol.

Real-Time Commitment Management. Y ahora le toca a Martí (al final todo queda en casa :-). Hablando, más o menos, de compromisos sociales en tiempo real. La idea es tratar de asegurar de que si un agente se compromete a realizar una tarea en un tiempo, va a cumplir su compromiso y se asegura de que se cumplen los tiempos acordados. Para eso, hace falta emplear técnicas de tiempo real que acoten el tiempo de ejecución de las tareas que forman el acuerdo. Emplea un CBR para analizar ejecuciones anteriores y predecir si los tiempos que se manejan actualmente son adecuados o no basándose en su experiencia.

Acaba la primera parte, así que ahora toca café. ¿Habrá pastelitos? Los he descubierto en este viaje y son deliciosos. ¡Siiiii! había pastelitos. Y otros de holandre que no había probado. La verdad es que en Lisboa hacen un hojaldre excelente. Pero antes de que esto se convierta en un blog gastronómico, voy a seguir con el workshop.

A Trust Model to Recommend Knowledge Objects in CoPs. CoPs (Communties of Practice) son grupos de personas con intereses comunes. Utilizan agentes para representar los miembros de la comunidady sobre él establecen un modelo de confianza para compartir conocimiento dentro de la comunidad. Usan 4 factores: la posición (en una jerarquía), la experiencia pasada, la intuición (similaridad con perfiles de usuario) y la experiencia (habilidades y conocimiento para desempeñar la tarea). Estos cuatro factores se ponderan para obtener una medida de trust global. En el ejemplo vuelven a aparecer managers que lo controlan todo. Los odio, ¿cuando alguién hablará de comunidades autoorganizadas pero de verdad? Al final, un prototipo para validar cosas. ¿Sigue sin haber agentes de verdad? ¿Por quñe los agentes no ayudan a los usuarios humanos?

ALZ-MAS 2.0: Distributing Resources for Enhancing Performance. Cosas parecidas a lo que hacemos nosotros (claro, por eso trabajamos juntos :-) Los agentes ‘pierden peso’ y construyen sus capacidades como servicios. Su modelo, FUSION@, permite la comunicación de agentes, aplicaciones y servicios como una capa intermedia (middleware) que usa los agentes para proporcionar servicios complejos de alto nivel a los usuarios, basándose en piezas de código autónomas y rehusables (servicios). El conocimiento está fuera de los agentes y estos se pueden considerar casi gestores de conversaciones. El núcleo de la plataforma está base en un servicio de planing basado en casos (una mezcla de planificador y CBR -> mirarlo para lo que estamos haciendo para conseguir serviciso de tiempo real garantizados).

Dialogue Systems Domain Interaction Using Reinforcement Learning.

A distributed algorithm for the Holonic Global Road Transportation System.