In large, distributed sensor web systems, allocating resources to complex user tasks presents significant challenges. Sensor web users and their desired tasks have differing importance in the sensor web, so designing a multi-agent framework to yield allocations that are both fair and efficient (high utility) is a challenging research problem. With complex, hierarchically-decomposable tasks, individual subtasks could potentially be assigned to a number of agents (e.g., when there is overlap in sensor or data processing capability among constituent sensor networks). Efficient allocation of subtasks within the proposed multi-agent framework presents additional challenges. Both of these research problems are further compounded by the dynamic nature of the sensor web, in which both desired tasks and resource availability change significantly with time and environmental conditions. This paper presents an overview of these research challenges and a solution approach employing broker agents in a novel variation of the contract net protocol (CNP) for fair and efficient allocation of complex tasks.

Deadline pressures, unexpected events, and combinatorial numbers of possible courses of action often lead a person to decide which activity she will begin next without considering a full enumeration of possible schedules, and thus, without a full awareness of the implications that her choice will have on the rest of her day's schedule. Furthermore, people suffering from cognitive impairments may lack the abilities to perform such reasoning in the first place. The goal of my thesis is to develop foundational technologies for computational agents that augment the abilities of people who face the above challenges to reason about the implications of scheduling. In particular, I develop, integrate, and evaluate new techniques for solving multi-agent Hybrid Scheduling Problems, which support coordinated activity selection and scheduling for human users.

Multi-agent pathfinding is a challenging problem with many important real-life applications. Despite its completeness and solution solution optimality guarantees, a global search such as centralised A* has little practical value due to its exponential state space. Scalability to larger problems has been achieved with decentralized approaches, which decompose an initial problem into a series of searches. Even though their CPU and memory requirements are significantly lower, existing decentralized methods are incomplete and provide no criteria to distinguish between problems that can successfully be solved and problems where such algorithms fail. Further, no guarantees are given with respect to the running time, the memory requirements, and the quality of the computed solutions. Addressing such limitations is the central motivation for our recent and current work on identifying a tractable class of problems and developing an algorithm that is complete on this class of problems, with guarantees of low-polynomial running time, memory requirements and solution length.

This thesis aims to provide a foundation for designing computer agents able to work better with people and with other agents in heterogeneous groups. When agents work together on a collaborative activity, in addition to performing their share of the activity, they may be able to help one another and thus improve the collective utility. The thesis specifically focuses on investigating the question of how, when and what kinds of helpful behavior should emerge when agents collaborate, taking into account the costs of a helpful action. It considers collaborative activities that take place in settings in which there is uncertainty about agents' capabilities and about the state of the world. To ensure that helpful behavior improves the overall benefit of the collaboration, the thesis incorporates decision-theoretic mechanisms for managing helpful behavior into existing formalizations of collaborative activity. It provides an investigation of the way people perceive the usefulness of helpful actions when proposed by a computer agent. It proposes incentives for facilitating collaboration among self-interested agents. In addition to these theoretical and empirical contributions, my findings are applied to several real-life application domains with different characteristics.

In this paper, an event-centric commodity trading simulation powered by the multiagent framework is presented. The purpose of this simulation platform is for training novice traders. The simulation is progressed by announcing news events that affect various aspects of the commodity supply chain. Upon receiving these events, market agents that play the roles of producers, consumers, and speculators would adjust their views on the market and act accordingly. Their actions would be based on their roles and also their private information, and collectively they shape the market dynamics. This simulation has been effectively deployed for several training sessions. We will present the underlying technologies that are employed and discuss the practical significance of such platform.

Agents and market mechanisms are widely elaborated and applied to automate interaction and decision processes among others in robotics, for decentralized control in sensor networks and by algorithmic traders in financial markets. Currently there is a high demand of efficient mechanisms for the provisioning, usage and allocation of distributed services in the Cloud. Such mechanisms and processes are not manually manageable and require decisions taken in quasi real-time. Thus agent decisions should automatically adapt to changing conditions and converge to optimal values. This paper presents a bidding strategy, which is capable of automating the bid generation and utility maximization processes of consumers and providers by the interaction with markets as well as to converge to optimal values. The bidding strategy is applied to the consumer side against benchmark bidding strategies and its behavior and convergence are evaluated in two market mechanisms, a centralized and a decentralized one.

This paper illustrates how we create a software agent by employing FALCON, a self-organizing neural network that performs reinforcement learning, to play a well-known first person shooter computer game known as Unreal Tournament 2004. Through interacting with the game environment and its opponents, our agent learns in real-time without any human intervention. Our agent bot participated in the 2K Bot Prize competition, similar to the \emph{Turing test} for intelligent agents, wherein human judges were tasked to identify whether their opponents in the game were human players or virtual agents. To perform well in the competition, an agent must act like human and be able to adapt to some changes made to the game. Although our agent did not emerge top in terms of human-like, the overall performance of our agent was encouraging as it acquired the highest game score while staying convincing to be human-like in some judges' opinions.

This paper describes a novel approach based on a combination of techniques in AI, parallel computing, and network science to address an important problem in social sciences and public health: planning and responding in the event of epidemics. Spread of infectious disease is an important societal problem -- human behavior, social networks, and the civil infrastructures all play a crucial role in initiating and controlling such epidemic processes.  We specifically consider the economic and social effects of realistic interventions  proposed and adopted by public health officials and behavioral changes  of  private citizens in the event of a ``flu-like'' epidemic. Our results provide new insights for developing robust public policies that can prove useful for epidemic planning.

There have been several highway traffic models proposed based on cellular automata. The simplest one is elementary cellular automaton rule 184. We extend this model to city traffic with cellular automata coupled at intersections using only rules 184, 252, and 136. The simplicity of the model offers a clear understanding of the main properties of city traffic and its phase transitions. We use the proposed model to compare two methods for coordinating traffic lights: a green-wave method that tries to optimize phases according to expected flows and a self-organizing method that adapts to the current traffic conditions. The self-organizing method delivers considerable improvements over the green-wave method. For low densities, the self-organizing method promotes the formation and coordination of platoons that flow freely in four directions, i.e. with a maximum velocity and no stops. For medium densities, the method allows a constant usage of the intersections, exploiting their maximum flux capacity. For high densities, the method prevents gridlocks and promotes the formation and coordination of "free-spaces" that flow in the opposite direction of traffic.

The Tactical Language and Culture Training System (TLCTS) helps people quickly acquire communicative skills in foreign languages and cultures.  More than 40,000 learners worldwide have used TLCTS courses.  TLCTS utilizes artificial intelligence technologies during the authoring process, and at run time to process learner speech, engage in dialog, and evaluate and assess learner performance. This paper describes the architecture of TLCTS and the artificial intelligence technologies that it employs, and presents results from multiple evaluation studies that demonstrate the benefits of learning foreign language and culture using this approach.