This thesis focuses on the problem of temporal planning under uncertainty with explicit safety guarantees, which are enforced by means of chance constraints. We aim at elevating the level in which operators interact with autonomous agents and specify their desired behavior, while retaining a keen sensitivity to risk. Instead of relying on unconditional sequences, our goal is to allow contingent plans to be dynamically scheduled and conditioned on observations of the world while remaining safe. Contingencies add flexibility by allowing goals to be achieved through different methods, while observations allow the agent to adapt to the environment. We demonstrate the usefulness of our chance-constrained temporal planning approaches in real-world applications, such as partially observable power supply restoration and collaborative human-robot manufacturing.

In this thesis, we focus on automated advising agents. The advice given is a form of relating recommendations or guidance from an automated agent to its human user. Providing the right advice at the right time is extremely complex, and requires a good adaptation to human desires and changing environments. We propose a novel methodology for designing automated advising agents and evaluate it in three real world environments. Our intelligent advising agents were evaluated through extensive field trials, with hundreds of human subjects. A significant increase in human performance as well as a high level of user satisfaction was recorded when they were equipped with our agents.

In decision-theoretic planning problems, such as (partially observable) Markov decision problems or coordination graphs, agents typically aim to optimize a scalar value function. However, in many real-world problems agents are faced with multiple possibly conflicting objectives. In such multi-objective problems, the value is a vector rather than a scalar, and we need methods that compute a coverage set, i.e., a set of solutions optimal for all possible trade-offs between the objectives. In this project propose new multi-objective planning methods that compute the so-called convex coverage set (CCS): the coverage set for when policies can be stochastic, or the preferences are linear. We show that the CCS has favorable mathematical properties, and is typically much easier to compute that the Pareto front, which is often axiomatically assumed as the solution set for multi-objective decision problems.

My research goal involves simultaneously addressing statistical and computational tradeoffs encountered in modern data analysis and high-dimensional machine learning (eg: hypothesis testing, regression, classification). My future interests include incorporating additional constraints like privacy or communication, and settings involving hidden utilities of multiple cooperative agents or competitive adversaries.

Our research is within the area of artificial intelligence and multi-agent systems. More specifically, we focus on evaluating trust relationships between the agents in multi-agent e-marketplaces and sensor networks and aim to address the following problems: 1) how to identify a trustworthy (good quality) agent; 2) how to cope with dishonest advisors i.e., agents who provide misleading opinions about others.

Decentralized partially observable Markov decision processes (Dec-POMDPs) provide a general model for decision-making under uncertainty in cooperative decentralized settings, but are difficult to solve optimally (NEXP-Complete). As a new way of solving these problems, we recently introduced a method for transforming a Dec-POMDP into a continuous-state deterministic MDP with a piecewise-linear and convex value function. This new Dec-POMDP formulation, which we call an occupancy MDP, allows powerful POMDP and continuous-state MDP methods to be used for the first time. However, scalability remains limited when the number of agents or problem variables becomes large. In this paper, we show that, under certain separability conditions of the optimal value function, the scalability of this approach can increase considerably. This separability is present when there is locality of interaction between agents, which can be exploited to improve performance. Unlike most previous methods, the novel continuous-state MDP algorithm retains optimality and convergence guarantees. Results show that the extension using separability can scale to a large number of agents and domain variables while maintaining optimality.

Before deploying a software system we need to assure ourselves (and stakeholders) that the system will behave correctly. This assurance is usually done by testing the system. However, it is intuitively obvious that adaptive systems, including agent-based systems, can exhibit complex behaviour, and are thus harder to test. In this paper we examine this "obvious intuition" in the case of Belief-Desire-Intention (BDI) agents, by analysing the number of paths through BDI goal-plan trees. Our analysis confirms quantitatively that BDI agents are hard to test, sheds light on the role of different parameters, and highlights the enormous difference made by failure handling.

We understand a sociotechnical system as a microsociety in which autonomous parties interact with and about technical objects. We define governance as the administration of such a system by its participants. We develop an approach for governance based on a computational representation of norms. Our approach has the benefit of capturing stakeholder needs precisely while yielding adaptive resource allocation in the face of changes both in stakeholder needs and the environment. We are currently extending this approach to address the problem of secure collaboration and to contribute to the emerging science of cybersecurity.

A clear separation of the constitutive from the regulative specification would bring many advantages, mostly as direct We analyze the emerging trends from research on effects of the obtained modularity: easier reuse of actions in multi-agent interaction protocols, on workflows and different contexts, easier customization on the protocol, easier on business processes. We propose a definition of composition of protocols. As a consequence, MAS would gain commitment-based interaction protocols, characterized greater openness, interoperability, and modularity of design.

In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of multiple (even infinite) equilibria and inherently large strategy spaces. In this paper, we introduce a method to reduce the strategy space of two-player general-sum RSGs to a handful of expert strategies. This process, called mega, effectually reduces an RSG to a bandit problem. We show that the resulting strategy space preserves several important properties of the original RSG, thus enabling a learner to produce robust strategies within a reasonably small number of interactions. To better establish strengths and weaknesses of this approach, we empirically evaluate the resulting learning system against other algorithms in three different RSGs.