Showing papers in "Autonomous Agents and Multi-Agent Systems in 2012"

A multiagent approach to managing air traffic flow

Abstract: Intelligent air traffic flow management is one of the fundamental challenges facing the Federal Aviation Administration (FAA) today. FAA estimates put weather, routing decisions and airport condition induced delays at 1,682,700 h in 2007 (FAA OPSNET Data, US Department of Transportation website, http://www.faa.gov/data_statistics/ ), resulting in a staggering economic loss of over $41 billion (Joint Economic Commission Majority Staff, Your flight has been delayed again, 2008). New solutions to the flow management are needed to accommodate the threefold increase in air traffic anticipated over the next two decades. Indeed, this is a complex problem where the interactions of changing conditions (e.g., weather), conflicting priorities (e.g., different airlines), limited resources (e.g., air traffic controllers) and heavy volume (e.g., over 40,000 flights over the US airspace) demand an adaptive and robust solution. In this paper we explore a multiagent algorithm where agents use reinforcement learning (RL) to reduce congestion through local actions. Each agent is associated with a fix (a specific location in 2D space) and has one of three actions: setting separation between airplanes, ordering ground delays or performing reroutes. We simulate air traffic using FACET which is an air traffic flow simulator developed at NASA and used extensively by the FAA and industry. Our FACET simulations on both artificial and real historical data from the Chicago and New York airspaces show that agents receiving personalized rewards reduce congestion by up to 80% over agents receiving a global reward and by up to 90% over a current industry approach (Monte Carlo estimation).

Agents for games and simulations

Abstract: Serious computer games have become increasingly popular; they also require more elaborate and natural behavior on the part of Non-Playing Characters. The more elaborate the interactions among characters are during a game, the more difficult it is to design these characters without the use of specialized tools geared towards implementing intelligent agents in a modular way. This thus seems to be an excellent area for the application of intelligent agent technology, which for the past two decades has been developed based on design concepts such as Goals, Intentions, Plans and Beliefs. A first attempt at connecting game engines with these types of agents has been made with Gamebots [1]. Gamebots provides an infrastructure that allows the interfacing of any agent platform to the computer game Unreal Tournament. Gamebots manages the provision of relevant information regarding the game state, while delivering commands for actions from the agents to Unreal. More recently, this package was used as the basis for more extensive middleware called Pogamut [2]. Although the aforementionedmiddleware does allow the interfacing of agents to the game engine, that in itself does not guarantee proper behavior of the agents in the game. In the workshop series on Agents for Games and Simulations [3,4], started in 2009, issues regarding the connection of agent technology to game engines has been discussed. Most of these issues derive from the fact that game engines are typically designed to be in total control of the game’s progress. On the other hand one, of the major attributes of agents developed on MAS platforms is that they are autonomous (to some extent) and interact asynchronously. We want to exploit the benefits of having agents deciding intelligently and autonomously about their next actions, while not losing control of the game. This balancing act leads to three broad categories of issues. The first category is that of technical issues; an important issue in this category is that of coping with real-time environments. Unfortunately, agent technology has hardly bothered with real-time issues up until now. A major exception is the use of agent technology in robotics, where one obviously also has to deal with real-time environments. Maybe this is one of the reasons that, in robotics, people do not use standard (BDI) agent platforms as basis for

Multiagent task allocation in social networks

Abstract: This paper proposes a new variant of the task allocation problem, where the agents are connected in a social network and tasks arrive at the agents distributed over the network. We show that the complexity of this problem remains NP-complete. Moreover, it is not approximable within some factor. In contrast to this, we develop an efficient greedy algorithm for this problem. Our algorithm is completely distributed, and it assumes that agents have only local knowledge about tasks and resources. We conduct a broad set of experiments to evaluate the performance and scalability of the proposed algorithm in terms of solution quality and computation time. Three different types of networks, namely small-world, random and scale-free networks, are used to represent various social relationships among agents in realistic applications. The results demonstrate that our algorithm works well and also that it scales well to large-scale applications. In addition we consider the same problem in a setting where the agents holding the resources are self-interested. For this, we show how the optimal algorithm can be used to incentivize these agents to be truthful. However, the efficient greedy algorithm cannot be used in a truthful mechanism, therefore an alternative, cluster-based algorithm is proposed and evaluated.

Towards verifying contract regulated service composition

Abstract: We report on a novel approach to (semi-)automatically compile and verify contract-regulated service compositions implemented as multi-agent systems. We model web service behaviours and the contracts governing them as WSBPEL specification. We use the formalism of temporal-epistemic logic, suitably extended to deal with compliance/violations of contracts, to specify properties of service compositions. We compile the WSBPEL behaviours into a specialised system description language ISPL, to be used with the model checker MCMAS to verify the behaviours automatically. We illustrate these concepts using a motivating example whose state space is approximately 106 and discuss experimental results.

Creating adaptive affective autonomous NPCs

Abstract: The paper reports work to create believable autonomous Non Player Characters in Video games in general and educational role play games in particular. It aims to increase their ability to respond appropriately to the player's actions both cognitively and emotionally by integrating two models: the cognitive appraisal-based FAtiMA architecture, and the drives-based PSI model. We discuss the modelling of adaptive affective autonomous characters based on a biologically-inspired theory of human action regulation taking into account perception, motivation, emotions, memory, learning and planning. These agents populate an educational Role Playing Game, ORIENT (Overcoming Refugee Integration with Empathic Novel Technology) dealing with the cultural-awareness problem for children aged 13---14.

A formal model of emotions for an empathic rational dialog agent

Abstract: Recent research has shown that virtual agents expressing empathic emotions toward users have the potential to enhance human---machine interaction. To provide empathic capabilities to a rational dialog agent, we propose a formal model of emotions based on an empirical and theoretical analysis of the users' conditions of emotion elicitation. The emotions are represented by particular mental states of the agent, composed of beliefs, uncertainties and intentions. This semantically grounded formal representation enables a rational dialog agent to identify from a dialogical situation the empathic emotion that it should express. An implementation and an evaluation of an empathic rational dialog agent have enabled us to validate the proposed model of empathy.

Winner determination in voting trees with incomplete preferences and weighted votes

Abstract: In multiagent settings where agents have different preferences, preference aggregation can be an important issue. Voting is a general method to aggregate preferences. We consider the use of voting tree rules to aggregate agents' preferences. In a voting tree, decisions are taken by performing a sequence of pairwise comparisons in a binary tree where each comparison is a majority vote among the agents. Incompleteness in the agents' preferences is common in many real-life settings due to privacy issues or an ongoing elicitation process. We study how to determine the winners when preferences may be incomplete, not only for voting tree rules (where the tree is assumed to be fixed), but also for the Schwartz rule (in which the winners are the candidates winning for at least one voting tree). In addition, we study how to determine the winners when only balanced trees are allowed. In each setting, we address the complexity of computing necessary (respectively, possible) winners, which are those candidates winning for all completions (respectively, at least one completion) of the incomplete profile. We show that many such winner determination problems are computationally intractable when the votes are weighted. However, in some cases, the exact complexity remains unknown. Since it is generally computationally difficult to find the exact set of winners for voting trees and the Schwartz rule, we propose several heuristics that find in polynomial time a superset of the possible winners and a subset of the necessary winners which are based on the completions of the (incomplete) majority graph built from the incomplete profiles.

Sequentially optimal repeated coalition formation under uncertainty

Abstract: Coalition formation is a central problem in multiagent systems research, but most models assume common knowledge of agent types. In practice, however, agents are often unsure of the types or capabilities of their potential partners, but gain information about these capabilities through repeated interaction. In this paper, we propose a novel Bayesian, model-based reinforcement learning framework for this problem, assuming that coalitions are formed (and tasks undertaken) repeatedly. Our model allows agents to refine their beliefs about the types of others as they interact within a coalition. The model also allows agents to make explicit tradeoffs between exploration (forming "new" coalitions to learn more about the types of new potential partners) and exploitation (relying on partners about which more is known), using value of information to define optimal exploration policies. Our framework effectively integrates decision making during repeated coalition formation under type uncertainty with Bayesian reinforcement learning techniques. Specifically, we present several learning algorithms to approximate the optimal Bayesian solution to the repeated coalition formation and type-learning problem, providing tractable means to ensure good sequential performance. We evaluate our algorithms in a variety of settings, showing that one method in particular exhibits consistently good performance in practice. We also demonstrate the ability of our model to facilitate knowledge transfer across different dynamic tasks.

AutoMed: an automated mediator for multi-issue bilateral negotiations

Abstract: In this paper, we present AutoMed, an automated mediator for multi-issue bilateral negotiation under time constraints. AutoMed elicits the negotiators preferences and analyzes them. It monitors the negotiations and proposes possible solutions for resolving the conflict. We conducted experiments in a simulated environment. The results show that negotiations mediated by AutoMed are concluded significantly faster than non-mediated ones and without any of the negotiators opting out. Furthermore, the subjects in the mediated negotiations are more satisfied with the resolutions than the subjects in the non-mediated negotiations.

Reputation-based decisions for logic-based cognitive agents

Abstract: Computational trust and reputation models have been recognized as one of the key technologies required to design and implement agent systems. These models manage and aggregate the information needed by agents to efficiently perform partner selection in uncertain situations. For simple applications, a game theoretical approach similar to that used in most models can suffice. However, if we want to undertake problems found in socially complex virtual societies, we need more sophisticated trust and reputation systems. In this context, reputation-based decisions that agents make take on special relevance and can be as important as the reputation model itself. In this paper, we propose a possible integration of a cognitive reputation model, Repage, into a cognitive BDI agent. First, we specify a belief logic capable to capture the semantics of Repage information, which encodes probabilities. This logic is defined by means of a two first-order languages hierarchy, allowing the specification of axioms as first-order theories. The belief logic integrates the information coming from Repage in terms if image and reputation, and combines them, defining a typology of agents depending of such combination. We use this logic to build a complete graded BDI model specified as a multi-context system where beliefs, desires, intentions and plans interact among each other to perform a BDI reasoning. We conclude the paper with an example and a related work section that compares our approach with current state-of-the-art models.

Emotions in autonomous agents: comparative analysis of mechanisms and functions

Abstract: Emotion mechanisms are often used in artificial agents as a method of improving action selection. Comparisons between agents are difficult due to a lack of unity between the theories of emotion, tasks of agents and types of action selection utilised. A set of architectural qualities is proposed as a basis for making comparisons between agents. An analysis of existing agent architectures that include an emotion mechanism can help to triangulate design possibilities within the space outlined by these qualities. With this in mind, twelve autonomous agents incorporating an emotion mechanism into action selection are selected for analysis. Each agent is dissected using these architectural qualities (the agent architecture, the action selection mechanism, the emotion mechanism and emotion state representation, along with the emotion model it is based on). This helps to place the agents within an architectural space, highlights contrasting methods of implementing similar theoretical components, and suggests which architectural aspects are important to performance of tasks. An initial framework is introduced, consisting of a series of recommendations for designing emotion mechanisms within artificial agents, based on correlations between emotion roles performed and the aspects of emotion mechanisms used to perform those roles. The conclusion discusses how problems with this type of research can be resolved and to what extent development of a framework can aid future research.

A brief introduction to agent mining

Abstract: Agent mining is an emerging interdisciplinary area that integrates multiagent systems, data mining and knowledge discovery, machine learning and other relevant areas. It brings new opportunities to tackling issues in relevant fields more efficiently by engaging together the individual technologies. It will also bring about symbiosis and symbionts that combine advantages from the corresponding constituent systems. In this editorial, we briefly introduce the concept of agent mining, the main areas of research, and challenges and opportunities in agent mining. Finally, we give an overview of the papers in this special issue.

Using argumentation to model agent decision making in economic experiments

Abstract: In this paper we demonstrate how a qualitative framework for decision making can be used to model scenarios from experimental economic studies and we show how our approach explains the results that have been reported from such studies. Our framework is an argumentation-based one in which the social values promoted or demoted by alternative action options are explicitly represented. Our particular representation is used to model the Dictator Game and the Ultimatum Game, which are simple interactions in which it must be decided how a sum of money will be divided between the players in the games. Studies have been conducted into how humans act in such games and the results are not explained by a decision-model that assumes that the participants are purely self-interested utility-maximisers. Some studies further suggest that differences in choices made in different cultures may reflect their day to day behaviour, which can in turn be related to the values of the subjects, and how they order their values. In this paper we show how these interactions can be modelled in agent systems in a framework that makes explicit the reasons for the agents' choices based upon their social values. Our framework is intended for use in situations where agents are required to be adaptable, for example, where agents may prefer different outcome states in transactions involving different types of counter-parties.

Addressing stability issues in mediated complex contract negotiations for constraint-based, non-monotonic utility spaces

Abstract: Negotiating contracts with multiple interdependent issues may yield non- monotonic, highly uncorrelated preference spaces for the participating agents. These scenarios are specially challenging because the complexity of the agents' utility functions makes traditional negotiation mechanisms not applicable. There is a number of recent research lines addressing complex negotiations in uncorrelated utility spaces. However, most of them focus on overcoming the problems imposed by the complexity of the scenario, without analyzing the potential consequences of the strategic behavior of the negotiating agents in the models they propose. Analyzing the dynamics of the negotiation process when agents with different strategies interact is necessary to apply these models to real, competitive environments. Specially problematic are high price of anarchy situations, which imply that individual rationality drives the agents towards strategies which yield low individual and social welfares. In scenarios involving highly uncorrelated utility spaces, "low social welfare" usually means that the negotiations fail, and therefore high price of anarchy situations should be avoided in the negotiation mechanisms. In our previous work, we proposed an auction-based negotiation model designed for negotiations about complex contracts when highly uncorrelated, constraint-based utility spaces are involved. This paper performs a strategy analysis of this model, revealing that the approach raises stability concerns, leading to situations with a high (or even infinite) price of anarchy. In addition, a set of techniques to solve this problem are proposed, and an experimental evaluation is performed to validate the adequacy of the proposed approaches to improve the strategic stability of the negotiation process. Finally, incentive-compatibility of the model is studied.

Deliberation dialogues for reasoning about safety critical actions

Abstract: In this paper we present the argument-based model proCLAIM, intended to provide a setting for heterogeneous agents to deliberate over safety critical actions. To achieve this purpose proCLAIM features a Mediator Agent with three main tasks: (1) guiding the participating agents in what their valid dialectical moves are at each stage of the dialogue; (2) deciding whether submitted arguments should be accepted on the basis of their relevance; and finally, (3) evaluating the accepted arguments in order to provide an assessment of whether the proposed action should or should not be undertaken. The main focus in this paper is the proposal of a set of reasoning patterns, represented in terms of argument schemes and critical questions, intended to automatise deliberations on whether a proposed action can safely be performed. We aim to motivate the importance of these schemes and critical questions for: (a) the Mediator Agent's guiding task that allows for a highly focused deliberation; (b) the effective participation of heterogeneous agents; and (c) enabling the reuse of previous similar deliberations in order to evaluate arguments on an evidential basis.

Modeling agents based on aspiration adaptation theory

Abstract: Creating agents that realistically simulate and interact with people is an important problem. In this paper we present strong empirical evidence that such agents should be based on bounded rationality, and specifically on key elements from Aspiration Adaptation Theory (AAT). First, we analyzed the strategies people described they would use to solve two relatively basic optimization problems involving one and two parameters. Second, we studied the agents a different group of people wrote to solve these same problems. We then studied two realistic negotiation problems involving five and six parameters. Again, first we studied the negotiation strategies people used when interacting with other people. Then we studied two state of the art automated negotiation agents and negotiation sessions between these agents and people. We found that in both the optimizing and negotiation problems the overwhelming majority of automated agents and people used key elements from AAT, even when optimal solutions, machine learning techniques for solving multiple parameters, or bounded techniques other than AAT could have been implemented. We discuss the implications of our findings including suggestions for designing more effective agents for game and simulation environments.

Learning opponent's preferences for effective negotiation: an approach based on concept learning

Abstract: We consider automated negotiation as a process carried out by software agents to reach a consensus. To automate negotiation, we expect agents to understand their user's preferences, generate offers that will satisfy their user, and decide whether counter offers are satisfactory. For this purpose, a crucial aspect is the treatment of preferences. An agent not only needs to understand its own user's preferences, but also its opponent's preferences so that agreements can be reached. Accordingly, this paper proposes a learning algorithm that can be used by a producer during negotiation to understand consumer's needs and to offer services that respect consumer's preferences. Our proposed algorithm is based on inductive learning but also incorporates the idea of revision. Thus, as the negotiation proceeds, a producer can revise its idea of the consumer's preferences. The learning is enhanced with the use of ontologies so that similar service requests can be identified and treated similarly. Further, the algorithm is targeted to learning both conjunctive as well as disjunctive preferences. Hence, even if the consumer's preferences are specified in complex ways, our algorithm can learn and guide the producer to create well-targeted offers. Further, our algorithm can detect whether some preferences cannot be satisfied early and thus consensus cannot be reached. Our experimental results show that the producer using our learning algorithm negotiates faster and more successfully with customers compared to several other algorithms.

A negotiation framework for linked combinatorial optimization problems

Abstract: We tackle the challenge of applying automated negotiation to self-interested agents with local but linked combinatorial optimization problems. Using a distributed production scheduling problem, we propose two negotiation strategies for making concessions in a joint search space of agreements. In the first strategy, building on Lai and Sycara (Group Decis Negot 18(2):169---187, 2009), an agent concedes on local utility in order to achieve an agreement. In the second strategy, an agent concedes on the distance in an attribute space while maximizing its local utility. Lastly, we introduce a Pareto improvement phase to bring the final agreement closer to the Pareto frontier. Experimental results show that the new attribute-space negotiation strategy outperforms its utility-based counterpart on the quality of the agreements and the Pareto improvement phase is effective in approaching the Pareto frontier. This article presents the first study of applying automated negotiation to self-interested agents each with a local, but linked, combinatorial optimization problem.

Rich socio-cognitive agents for immersive training environments: case of NonKin Village

Abstract: Demand is on the rise for scientifically based human-behavior models that can be quickly customized and inserted into immersive training environments to recreate a given society or culture. At the same time, there are no readily available science model-driven environments for this purpose (see survey in Sect. 2). In researching how to overcome this obstacle, we have created rich (complex) socio-cognitive agents that include a large number of social science models (cognitive, sociologic, economic, political, etc) needed to enhance the realism of immersive, artificial agent societies. We describe current efforts to apply model-driven development concepts and how to permit other models to be plugged in should a developer prefer them instead. The current, default library of behavioral models is a metamodel, or authoring language, capable of generating immersive social worlds. Section 3 explores the specific metamodels currently in this library (cognitive, socio-political, economic, conversational, etc.) and Sect. 4 illustrates them with an implementation that results in a virtual Afghan village as a platform-independent model. This is instantiated into a server that then works across a bridge to control the agents in an immersive, platform-specific 3D gameworld (client). Section 4 also provides examples of interacting in the resulting gameworld and some of the training a player receives. We end with lessons learned and next steps for improving both the process and the gameworld. The seeming paradox of this research is that as agent complexity increases, the easier it becomes for the agents to explain their world, their dilemmas, and their social networks to a player or trainee.

Agent and multi-agent applications to support distributed communities of practice: a short review

Abstract: This paper concerns the relationship between agents or multi-agent systems and distributed communities of practice. It presents a review of a number of agent and multi-agent applications with features that could contribute to supporting distributed communities of practice. The association is promising because of features like autonomy, pro-activity, flexibility or ability to integrate systems that characterize agents and multi-agent systems. Furthermore, such an association is a step towards building mixed communities of humans and artificial agents. To understand how agents and multi-agent systems could answer some of the needs of distributed communities of practice, we organize the analyzed applications into five different categories defined by considering the main activities of a community, namely: Individual Participation, Synchronous Interactions, Asynchronous Interactions, Publishing and Community Cultivation. Such a classification helps us identify the relevant features of the current technology and determine some that should be further developed, e.g. to support community coordination or gather information related to virtual communities. For each application we selected, we present its main approach and point out its potential interest.

Multi-agent based classification using argumentation from experience

Abstract: An approach to classification using a multi-agent system founded on an Argumentation from Experience paradigm is proposed. The technique is based on the idea that classification can be conducted as a process whereby a group of agents "argue" about the classification of a given case according to their experience as recorded in individual local data sets. The paper describes mechanisms whereby this can be achieved, which have been realised in the PISA framework. The framework allows both the possibility of agents operating in groups (coalitions) and migrating between groups. The proposed multi-agent classification using the Argumentation from Experience paradigm has been used to address standard, ordinal and unbalanced classification problems with good results. A full evaluation, in the context of these applications, is presented.

Implicit: a multi-agent recommendation system for web search

Abstract: For people with non-ordinary interests, it is hard to search for information on the Internet because search engines are impersonalized and are more focused on "average" individuals with "standard" preferences. In order to improve web search for a community of people with similar but specific interests, we propose to use the implicit knowledge contained in the search behavior of groups of users. We developed a multi-agent recommendation system called Implicit, which supports web search for groups or communities of people. In Implicit, agents observe behavior of their users to learn about the "culture" of the community with specific interests. They facilitate sharing of knowledge about relevant links within the community by means of recommendations. The agents also recommend contacts, i.e., who in the community is the right person to ask for a specific topic. Experimental evaluation shows that Implicit improves the quality of the web search in terms of precision and recall.

Diagnosis of coordination failures: a matrix-based approach

Abstract: One of the key requirements in many multi-agent teams is that agents coordinate specific aspects of their joint task. Unfortunately, this coordination may fail due to intermittent faults in sensor readings, communication faults, etc. A key challenge in the model-based diagnosis (MBD) of coordination failures is to represent a model of the coordination among the agents in a way that allows efficient detection and diagnosis, based on observation of the agents involved. Previously developed mechanisms are useful only for small groups of agents, since they represent the coordination with binary constraints. This paper presents a MBD approach to coordination failures in which non-binary constraints are allowed. This model has two inherent advantages: (1) the model enables to address real problems, (2) the model enables to address large groups by gathering multiple coordinations in one constraint. To solve the diagnosis problem, we propose a matrix-based approach to represent the basic building blocks of the MBD formalization. Theoretical and empirical evaluations show that this representation is efficient for large-scale teams.

Dependence in games and dependence games

Abstract: In the multi-agent systems community, dependence theory and game theory are often presented as two alternative perspectives on the analysis of agent interaction. The paper presents a formal analysis of a notion of dependence between players, given in terms of standard game-theoretic notions of rationality such as dominant strategy and best response. This brings the notion of dependence within the realm of game theory providing it with the sort of mathematical foundations which still lacks. Concretely, the paper presents two results: first, it shows how the proposed notion of dependence allows for an elegant characterization of a property of reciprocity for outcomes in strategic games; and second, it shows how the notion can be used to define new classes of coalitional games, where coalitions can force outcomes only in the presence of reciprocal dependencies.

Long-term information collection with energy harvesting wireless sensors: a multi-armed bandit based approach

Abstract: This paper reports on the development of a multi-agent approach to long-term information collection in networks of energy harvesting wireless sensors. In particular, we focus on developing energy management and data routing policies that adapt their behaviour according to the energy that is harvested, in order to maximise the amount of information collected given the available energy budget. In so doing, we introduce a new energy management technique, based on multi-armed bandit learning, that allows each agent to adaptively allocate its energy budget across the tasks of data sampling, receiving and transmitting. By using this approach, each agent can learn the optimal energy budget settings that give it efficient information collection in the long run. Then, we propose two novel decentralised multi-hop algorithms for data routing. The first proveably maximises the information throughput in the network, but can sometimes involve high communication cost. The second algorithm provides near-optimal performance, but with reduced computational and communication costs. Finally, we demonstrate that, by using our approaches for energy management and routing, we can achieve a 120% improvement in long-term information collection against state-of-the-art benchmarks.

Emergence of social networks via direct and indirect reciprocity

Abstract: Many models of social network formation implicitly assume that network properties are static in steady-state. In contrast, actual social networks are highly dynamic: allegiances and collaborations expire and may or may not be renewed at a later date. Moreover, empirical studies show that human social networks are dynamic at the individual level but static at the global level: individuals’ degree rankings change considerably over time, whereas network-level metrics such as network diameter and clustering coefficient are relatively stable. There have been some attempts to explain these properties of empirical social networks using agent-based models in which agents play social dilemma games with their immediate neighbours, but can also manipulate their network connections to strategic advantage. However, such models cannot straightforwardly account for reciprocal behaviour based on reputation scores (“indirect reciprocity”), which is known to play an important role in many economic interactions. In order to account for indirect reciprocity, we model the network in a bottom-up fashion: the network emerges from the low-level interactions between agents. By so doing we are able to simultaneously account for the effect of both direct reciprocity (e.g. “tit-for-tat”) as well as indirect reciprocity (helping strangers in order to increase one’s reputation). This leads to a strategic equilibrium in the frequencies with which strategies are adopted in the population as a whole, but intermittent cycling over different strategies at the level of individual agents, which in turn gives rise to social networks which are dynamic at the individual level but stable at the network level.

The adversarial activity model for bounded rational agents

Abstract: Multiagent research provides an extensive literature on formal Beliefs-Desires-Intentions (BDI) based models describing the notion of teamwork and cooperation However, multiagent environments are often not cooperative nor collaborative; in many cases, agents have conflicting interests, leading to adversarial interactions This form of interaction has not yet been formally defined in terms of the agents mental states, beliefs, desires and intentions This paper presents the Adversarial Activity model, a formal Beliefs-Desires-Intentions (BDI) based model for bounded rational agents operating in a zero-sum environment In complex environments, attempts to use classical utility-based search methods with bounded rational agents can raise a variety of difficulties (eg implicitly modeling the opponent as an omniscient utility maximizer, rather than leveraging a more nuanced, explicit opponent model) We define the Adversarial Activity by describing the mental states of an agent situated in such environment We then present behavioral axioms that are intended to serve as design principles for building such adversarial agents We illustrate the advantages of using the model as an architectural guideline by building agents for two adversarial environments: the Connect Four game and the Risk strategic board game In addition, we explore the application of our approach by analyzing log files of completed Connect Four games, and gain additional insights on the axioms' appropriateness

Koko: an architecture for affect-aware games

Abstract: The importance of affect in delivering engaging experiences in entertainment and educational games is well recognized. Yet, current techniques for building affect-aware games are limited, with the maintenance and use of affect in essence being handcrafted for each game. The Koko architecture describes a service-oriented middleware that reduces the burden of incorporating affect recognition into games, thereby enabling developers to concentrate on the functional and creative aspects of their applications. The Koko architecture makes three key contributions: (1) improving developer productivity by creating a reusable and extensible environment; (2) yielding an enhanced user experience by enabling independently developed games and other applications to collaborate and provide a more coherent user experience than currently possible; (3) enabling affective communication in multiplayer and social games. Further, Koko is intended to be used as an extension of existing game architectures. We recognize that complex games require additional third party libraries, such as game engines. To enable the required flexibility we define the interfaces of the Koko architecture in a formal manner, thereby enabling the implementation of those interfaces to readily adapt to the unique requirements of game's other architectural components and requirements.

Generalized framework for personalized recommendations in agent networks

Abstract: An agent network can be modeled as a directed weighted graph whose vertices represent agents and edges represent a trust relationship between the agents. This article proposes a new recommendation approach, dubbed LocPat, which can recommend trustworthy agents to a requester in an agent network. We relate the recommendation problem to the graph similarity problem, and define the similarity measurement as a mutually reinforcing relation. We understand an agent as querying an agent network to which it belongs to generate personalized recommendations. We formulate a query into an agent network as a structure graph applied in a personalized manner that reflects the pattern of relationships centered on the requesting agent. We use this pattern as a basis for recommending an agent or object (a vertex in the graph). By calculating the vertex similarity between the agent network and a structure graph, we can produce a recommendation based on similarity scores that reflect both the link structure and the trust values on the edges. Our resulting approach is generic in that it can capture existing network-based approaches merely through the introduction of appropriate structure graphs. We evaluate different structure graphs with respect to two main kinds of settings, namely, social networks and ratings networks. Our experimental results show that our approach provides personalized and flexible recommendations effectively and efficiently based on local information.

A framework for Multi-Agent Based Clustering

Abstract: A framework to support Multi-Agent Based Clustering (MABC) is described. A unique feature of the framework is that it provides mechanisms to allow agents to negotiate so as to improve an initial cluster configuration. The framework encourages a two phase approach to clustering. During the first phase clustering agents bid for records in the input data and form an initial cluster configuration. In the second phase (the negotiation phase) agents pass individual records to each other so as to improve the initial configuration. The communication framework and its operation is fully described in terms of the performatives used and from an algorithmic perspective. The reported evaluation was conducted using benchmark data sets. The results demonstrate that the supported agent negotiation produces enhanced clustering results.