In this paper we study the sequential strategic interactive setting of two-person, two-stage, seller-offers bargaining under uncertainty. We model the epistemology of the problem in a finite interactive decision-theoretic framework and solve it for three types of agents of successively increasing (epistemological) sophistication (or, capacity to represent and reason with higher orders of beliefs). In particular, we remove common knowledge assumptions about the agents' epistemology which, if made, would be sufficient to imply the existence of a, possibly unique, game-theoretic equilibrium solution. In this context, we present a characterization of a monotonic relationship between an agent's optimal behavior and its beliefs under a particular moment-based ordering. Further, based on this characterization, we present the \emph{spread-accumulate} sampling technique -- a method of sampling an agent's higher order belief by generating ``evenly dispersed" beliefs for which we (pre)compute offline solutions. Then, we present a method for approximating higher order prior belief update to arbitrary precision by identifying a (previously solved) belief ``closest" to the true belief. In addition, these methods directly suggest a mechanism for achieving a balance between efficiency and the quality of the approximation -- either by generating a large number of offline solutions or by allowing the agent to search online for a ``closer" belief in the vicinity of best current solution.

We study the problem of achieving cooperation between two self-interested agents that play a sequence of randomly generated normal form games, each game played only once. To achieve cooperation we extend a model used to explain cooperative behavior by humans. We show how a modification of a pre-regularized particle filter can be used to detect the cooperation level of the opponent and play accordingly. We examine how properties of the games affect the ability of an agent to detect cooperation and explore the effects of different environments and different levels of conflict. We present results obtained in simulation on hundreds of randomly generated games.

Informational conflicts in operational policies cause agents to run into situations where responding based on the rules in one policy violates the same or another policy. Static checking of these conflicts is infeasible and impractical in a dynamic environment. This paper discusses a practical approach to handling policy conflicts in real-time domains within the context of a hierarchical military command and control simulated system that consists of a central command, squad leaders and squad members. All the entities in the domain function according to preset communication and action protocols in order to perform successful missions. Each entity in the domain is equipped with an instance of a metacognitive component to provide on-board/on-time analysis of actions and recommendations during the operation of the system. The metacognitive component is the Metacognitive Loop (MCL) which is a general purpose anomaly processor designed to function as a cross-domain plugin system. It continuously monitors expectations and notices when they are violated, assesses the cause of the violation and guides the host system to an appropriate response. MCL makes use of three ontologies—indications, failures and responses—to perform the notice, assess and guide phases when a conflict occurs. Conflicts in the set of rules (within a policy or between policies) manifest as expectation violations in the real world. These expectation violations trigger nodes in the indication ontology which, in turn, activate associated nodes in the failure ontology. The responding failure nodes then activate the appropriate nodes in the response ontology. Depending on which response node gets activated, the actual response may vary from ignoring the conflict to prioritizing, modifying or deleting one or more conflicting rules.

Multi-Agent Plan Recognition (MAPR) seeks to identify the dynamic team structures and team behaviors from the observations of the activity-sequences of a set of intelligent agents, based on a library of known team-activities (plan library). It has important applications in analyzing data from automated monitoring, surveillance, and intelligence analysis in general. Recently, we have introduced a model for MAPR with a flat library structure, to study the complexity of basic MAPR, and also possibly its extensions in the future. Interestingly, this model makes fewer assumptions than existing models, and hence is more general. Therefore, as no existing algorithm would apply to this model, we have developed an hypothesis generation algorithm for this model, and adapted Knuth's Algorithm X for branch and bound search in the resulting hypothesis space. In this paper, we establish the time complexity of hypothesis generation in this model, propose and evaluate 3 different bounding criteria, and also empirically study the dependence of runtimes (hypothesis generation, and search times separately) on the model parameters.

A distributed non-hierarchical metacognitive architec- ture is one in which all meta-level reasoning compo- nents are subject to meta-level monitoring and manage- ment by other components. Such metacognitive distri- bution can support the robustness of distributed IT sys- tems in which humans and artificial agents are partic- ipants. However, robust metacognition also needs to be context-aware and use diversity in its reasoning and analysis methods. Both these requirements mean that an agent evaluates its reasoning within a “bigger picture” and that it can monitor this global picture from multi- ple perspectives. In particular, social context-awareness involves understanding the goals and concerns of users and organisations. In this paper, we first present a conceptual architecture for distributed metacognition with context-awareness and diversity. We then consider the challenges of apply- ing this architecture to autonomic management systems in scenarios where agents must collectively diagnose and respond to errors and intrusions. Such autonomic systems need rich semantic knowledge and diverse data sources in order to provide the necessary context for their metacognitive evaluations and decisions.

We present a game-theoretic model that formalizes core ideas of conversational grounding theory. This game-theoretic model is based on the concept of signaling games, originally proposed as a model of linguistic convention. We extend signaling games with an observation model, which allows for the possibility that the actions a dialog participant takes may only be partially observable to others. We then apply this model to the domain of referential communication tasks, a type of task commonly used in psycholinguistic experiments.

One of the critical factors for a successful cooperative relationship in a supply chain partnership is trust. Many real-world applications, such as Supply Chain Management (SCM), can be modeled using multi-agent systems. One shortcoming of current SCM models is that their trust models are ad hoc and do not have a strong theoretical basis. As a result, they are unable to model subtleties in agent behavior that can be used to build a more accurate trust model. We propose a trust model for SCM that is grounded in probabilistic game theory. In this model, trust can be gained through direct interactions and/or by asking for information from other trustworthy agents. We will use this model to simulate and study supply chain market behavior.

The most common solution concept for a strategic interaction situation is the Nash equilibrium, in which no agent can do better by deviating unilaterally. However, the Nash equilibrium underlays on the assumption of common information that is hardly verified in many practical situations. When information is not common, rational agents are assumed to learn from their observations to derive beliefs over their opponents' play and payoffs. In these situations, there are steady states composed of beliefs and strategies in which the strategies do not constitute a Nash equilibrium. These stable states are called in the game theory literature self-confirming equilibria. They are such that every agent plays the best response to her beliefs and these are correct on the equilibrium path, while off the equilibrium path they may be incorrect. We present some mathematical programming formulations for computing self-confirming equilibria and its refinements in two-player extensive-form games and we study their properties.

Wikis allow for collaborators to collect information about entities. In turn, such entity information can be used for AI tasks, such as information extraction. However, these collaborators are almost exclusively human users. Allowing arbitrary software agents to act as collaborators can greatly enrich a wiki since agents can contribute structured data to complement the human-contributed, unstructured-data. For instance, agents can import huge volumes of structured data about entities, enriching the pages, and agents can update wiki pages to reflect real-time information changes (e.g., win-loss records in sports). This paper describes an approach that allows for both arbitrary software agents and human users to collaborate. In particular, we address three key problems: agents updating the correct wiki pages, policies for agent updates, and sharing the schema across collaborators. Using our approach, we describe creating entity-focused wikis which include the ability to create dynamic categories of entities based on their wiki pages. These categories dynamically update their membership based upon real-world changes.

Collaborative filtering systems have been developed to manage information overload and improve discourse in online communities. In such systems, users rank content provided by other users on the validity or usefulness within their particular context. The goal is that "good" content will rise to prominence and "bad" content will fade into obscurity. These filtering mechanisms are not well-understood and have known weaknesses. For example, they depend on the presence of a large crowd to rate content, but such a crowd may not be present. Additionally, the community's decisions determine which voices will reach a large audience and which will be silenced, but it is not known if these decisions represent "the wisdom of crowds" or a "censoring mob." Our approach uses statistical machine learning to predict community ratings. By extracting features that replicate the community's verdict, we can better understand collaborative filtering, improve the way the community uses the ratings of their members, and design agents that augment community decision-making. Slashdot is an example of such a community where peers will rate each others' comments based on their relevance to the post. This work extracts a wide variety of features from the Slashdot metadata and posts' linguistic contents to identify features that can predict the community rating. We find that author reputation, use of pronouns, and author sentiment are salient. We achieve 76% accuracy predicting community ratings as good, neutral, or bad.