The evolution of the electronic sources connected through wide area networks like Internet has encouraged the development of new information gathering techniques that go beyond traditional information retrieval and WEB search methods. They use advanced techniques, like planning or constraint programming, to integrate and reason about hetereogeneous information sources. In this paper we describe MAPWEB. MAPWEB is a multiagent framework that integrates planning agents and WEB information retrieval agents. The goal of this framework is to deal with problems that require planning with information to be gathered from the WEB.

Creating artificial intelligent agents that are high-fidelity simulations of natural agents will require the engagement of behavioral scientists. However, agent programming systems that are accessible to behavioral scientists are too limited to create rich agents, and systems for creating rich agents are accessible mainly to computer scientists, not behavioral scientists. We are solving this problem by engaging behavioral scientists in the design of a programming language, and integrating reinforcement learning into the programming language. This strategy will help our language achieve adaptivity, modularity, and, most importantly, accessibility to behavioral scientists. In addition to allowing behavioral scientist to write rich agent programs, our language -- AFABL (A Friendly Behavior Language) -- will enable a true discipline of modular agent software engineering with broad implications for games, interactive storytelling, and social simulations.

My thesis investigates fault tolerance for cooperative agent systems that have some equivalent of self-replication and self-death. Utilizing biologically-inspired mechanisms, I increase multi-agent system robustness for faulty agents when it is unknown exactly which agent is malfunctioning. It is important to determine new ways to increase robustness of a system, as otherwise it cannot be guaranteed to function in all situations and thus cannot be relied upon. Robustness of a system allows agents to recover from errors and thus function continuously, an increasingly important trait as agent systems are deployed in real world scenarios such as sensor networks or surveillance systems where faulty or malicious nodes could disrupt application performance. To achieve robustness, there must either be prevention of all errors, or a technique for recovering from errors after they have occurred. My thesis creates a new fault tolerance mechanism inspired by cancer biology to remove faulty agents, and then re-applies the developed technique to study the removal of biological cancer cells in simulation.

The focus of my research is an agent-based system for optimizing spatial arrangements of plants on a landscape to maximize their growth and minimize their water use. The optimization criteria include a natural phenomenon known as facilitation, which is observed in water-scarce environments when larger shrubs serve as benefactors to smaller annuals by generating conditions that protect them from harsh afternoon sun. In my modeling and optimization system each plant is an agent with growth requirements. A plant agent's fitness at a given location is defined by a fitness function that includes those growth requirements and a penalty term designed to force facilitation. The landscape design is formulated as a combinatorial optimization problem with a discrete set of locations for each plant on a grid, a fixed number of plants, and a fitness function that defines the performance of a plant at a location. To evaluate the effectiveness of this approach, I applied a variety of search strategies, including simulated annealing and a new agent-based approach that mimics how plant communities evolve over time, to different collections of simulated plant types and landscapes and compared the fitness scores and spatial arrangments in the solutions. The fitness scores from the search strategies were comparable. The search strategies produced different spatial distributions of the larger plants, and all designs exhibited facilitation and lower water use.

My thesis contributes to the field of multi-agent systems by proposing a novel trust-based decision model for supply chain management.

Decentralized (PO)MDPs provide a rigorous framework for sequential multiagent decision making under uncertainty. However, their high computational complexity limits the practical impact. To address scalability and real-world impact, we focus on settings where a large number of agents primarily interact through complex joint-rewards that depend on their entire histories of states and actions. Such history-based rewards encapsulate the notion of events or tasks such that the team reward is given only when the joint-task is completed. Algorithmically, we contribute -- 1) A nonlinear programming (NLP) formulation for such event-based planning model; 2) A probabilistic inference based approach that scales much better than NLP solvers for a large number of agents; 3) A policy gradient based multiagent reinforcement learning approach that scales well even for exponential state- spaces.

The ability of an autonomous system to understand something about a human's intent is important to the success of many systems that involve both humans and autonomous agents. In this work, we consider the specific setting of a human passenger riding in an autonomous vehicle, where the passenger intends to go to or learn about a specific point of interest along the vehicle's route. In this setting, we seek to provide the vehicle with the ability to infer this point of interest using real-time gaze information. This is a difficult problem in that the inference must be designed in the context of the moving vehicle, i.e., in a dynamic environment with dynamic interest points. We propose here a solution to this problem via a novel methodology called Dynamic Interest Point Detection (DIPD) for inferring the point of interest corresponding to the human's intent using gaze tracking data and a dynamic Markov Random Field (MRF) model.

Recent works on gradient-based attacks and universal perturbations can adversarially modify images to bring down the accuracy of state-of-the-art classification techniques based on deep neural networks to as low as 10% on popular datasets like MNIST and ImageNet. The design of general defense strategies against a wide range of such attacks remains a challenging problem. In this paper, we derive inspiration from recent advances in the fields of cybersecurity and multi-agent systems and propose to use the concept of Moving Target Defense (MTD) for increasing the robustness of a set of deep networks against such adversarial attacks. To this end, we formalize and exploit the notion of differential immunity of an ensemble of networks to specific attacks. To classify an input image, a trained network is picked from this set of networks by formulating the interaction between a Defender (who hosts the classification networks) and their (Legitimate and Malicious) Users as a repeated Bayesian Stackelberg Game (BSG).We empirically show that our approach, MTDeep reduces misclassification on perturbed images for MNIST and ImageNet datasets while maintaining high classification accuracy on legitimate test images. Lastly, we demonstrate that our framework can be used in conjunction with any existing defense mechanism to provide more resilience to adversarial attacks than those defense mechanisms by themselves.

Social dilemmas, where mutual cooperation can lead to high payoffs but participants face incentives to cheat, are ubiquitous in multi-agent interaction. We wish to construct agents that cooperate with pure cooperators, avoid exploitation by pure defectors, and incentivize cooperation from the rest. However, often the actions taken by a partner are (partially) unobserved or the consequences of individual actions are hard to predict. We show that in a large class of games good strategies can be constructed by conditioning one's behavior solely on outcomes (i.e.

The two common design principles for agent-based models, KISS (Keep It Simple, Stupid) and KIDS (Keep It Descriptive, Stupid) offer limited traction for developing cognitive agents, who typically have strong ties to research findings and established theories of cognition. A KIKS principle (Keep It Knowledgeable, Stupid) is proposed to capture the fact that cognitive agents are grounded in published research findings and theory, rather than simply selecting parameters in an ad-hoc way. In short, KIKS suggests that modelers should not focus on how many parameters, but should instead focus on choosing the right research papers and implement each of their key parameters and mechanisms. Based on this principle, a design process for creating cognitive agents based on cognitive models is proposed. This process is centered around steps that cognitive agent designers are already consider (e.g., literature search, validation, implementing a computational model).