To be published as a chapter in'Adaptive Learning Methods for Nonlinear System Modeling', Elsevier Publishing, Eds. Abstract In this chapter, we analyze nonlinear filtering problems in distributed environments, e.g., sensor networks or peer-to-peer protocols. In these scenarios, the agents in the environment receive measurements in a streaming fashion, and they are required to estimate a common (nonlinear) model by alternating local computations and communications with their neighbors. We focus on the important distinction between single-task problems, where the underlying model is common to all agents, and multitask problems, where each agent might converge to a different model due to, e.g., spatial dependencies or other factors. Currently, most of the literature on distributed learning in the nonlinear case has focused on the single-task case, which may be a strong limitation in real-world scenarios. After introducing the problem and reviewing the existing approaches, we describe a simple kernel-based algorithm tailored for the multitask case. We evaluate the proposal on a simulated benchmark task, and we conclude by detailing currently open problems and lines of research.

A true lie is a lie that becomes true when announced. In a logic of announcements, where the announcing agent is not modelled, a true lie is a formula (that is false and) that becomes true when announced. We investigate true lies and other types of interaction between announced formulas, their preconditions and their postconditions, in the setting of Gerbrandy's logic of believed announcements, wherein agents may have or obtain incorrect beliefs. Our results are on the satisfiability and validity of instantiations of these semantically defined categories, on iterated announcements, including arbitrarily often iterated announcements, and on syntactic characterization. We close with results for iterated announcements in the logic of knowledge (instead of belief), and for lying as private announcements (instead of public announcements) to different agents. Detailed examples illustrate our lying concepts.

According to Clark's seminal work on common ground and grounding, participants collaborating in a joint activity rely on their shared information, known as common ground, to perform that activity successfully, and continually align and augment this information during their collaboration. Similarly, teams of human and artificial agents require common ground to successfully participate in joint activities. Indeed, without appropriate information being shared, using agent autonomy to reduce the workload on humans may actually increase workload as the humans seek to understand why the agents are behaving as they are. While many researchers have identified the importance of common ground in artificial intelligence, there is no precise definition of common ground on which to build the foundational aspects of multi-agent collaboration. In this paper, building on previously-defined modal logics of belief, we present logic definitions for four different types of common ground. We define modal logics for three existing notions of common ground and introduce a new notion of common ground, called salient common ground. Salient common ground captures the common ground of a group participating in an activity and is based on the common ground that arises from that activity as well as on the common ground they shared prior to the activity. We show that the four definitions share some properties, and our analysis suggests possible refinements of the existing informal and semi-formal definitions.

This paper considers the problem of decentralized optimization with a composite objective containing smooth and non-smooth terms. To solve the problem, a proximal-gradient scheme is studied. Specifically, the smooth and nonsmooth terms are dealt with by gradient update and proximal update, respectively. The studied algorithm is closely related to a previous decentralized optimization algorithm, PG-EXTRA [37], but has a few advantages. First of all, in our new scheme, agents use uncoordinated step-sizes and the stable upper bounds on step-sizes are independent from network topologies. The step-sizes depend on local objective functions, and they can be as large as that of the gradient descent. Secondly, for the special case without non-smooth terms, linear convergence can be achieved under the strong convexity assumption. The dependence of the convergence rate on the objective functions and the network are separated, and the convergence rate of our new scheme is as good as one of the two convergence rates that match the typical rates for the general gradient descent and the consensus averaging. We also provide some numerical experiments to demonstrate the efficacy of the introduced algorithms and validate our theoretical discoveries.

Problem decomposition and theory reformulation, integrated cognitive architectures for autonomous robots, distributed constraint satisfaction problems, semigroup theory and dynamical systems, category theory in software design. Interests include machine learning, approximation algorithms, on-line algorithms and planning systems. Calvin, William H. – Theoretical neurophysiologist and author of "The Cerebral Code", and "How Brains Think". Gesture and narrative language, animated agents, intonation, facial expression, computer vision. Intersection of computer science and game theory, computer science and economics, multiagent systems, automated negotiation and contracting.

Many real-world decision problems have multiple objectives. For example, when choosing a medical treatment plan, we want to maximize the efficacy of the treatment, but also minimize the side effects. These objectives typically conflict, e.g., we can often increase the efficacy of the treatment, but at the cost of more severe side effects. In this book, we outline how to deal with multiple objectives in decision-theoretic planning and reinforcement learning algorithms. To illustrate this, we employ the popular problem classes of multi-objective Markov decision processes (MOMDPs) and multi-objective coordination graphs (MO-CoGs).

Machines that can think for themselves - and perhaps turn on their creators as a result - have long been a fascination of science fiction. And creating robots that can learn without any input from humans is moving ever closer, thanks to the latest developments in artificial intelligence. One such project seeks to pit the wits of two AI algorithms against each other, with results that could one day lead to the emergence of such intelligent machines. Researchers have pitted AI algorithms against each other to create more realistic'imaginings' of the real world. Google's Generative Adversarial Network works by pitting two algorithms against each other, in an attempt to create convincing representations of the real world. These'imagined' digital creations - which can take the form of images, videos, sounds and other content - are based on data fed to the system.

As the development of artificial intelligence continues at breakneck speed, questions about whether we understand what we are getting ourselves into persist. One fear is that increasingly intelligent robots will take all our jobs. Another fear is that we will create a world where a superintelligence will one day decide that it has no need for humans. This fear is well-explored in popular culture, through books and films like the Terminator series. Another possibility is maybe the one that makes the most sense - since humans are the ones creating them, the machines and machine intelligences are likely to behave just like humans.

We determine the quality of randomized social choice algorithms in a setting in which the agents have metric preferences: every agent has a cost for each alternative, and these costs form a metric. We assume that these costs are unknown to the algorithms (and possibly even to the agents themselves), which means we cannot simply select the optimal alternative, i.e. the alternative that minimizes the total agent cost (or median agent cost). However, we do assume that the agents know their ordinal preferences that are induced by the metric space. We examine randomized social choice functions that require only this ordinal information and select an alternative that is good in expectation with respect to the costs from the metric. To quantify how good a randomized social choice function is, we bound the distortion, which is the worst-case ratio between the expected cost of the alternative selected and the cost of the optimal alternative. We provide new distortion bounds for a variety of randomized algorithms, for both general metrics and for important special cases. Our results show a sizable improvement in distortion over deterministic algorithms.

Consumers today have high expectations for customer service. They want service that is fast, personalized, and available wherever they are. Companies want to provide great service, but with new channels such as web chat, messaging apps, and in-app support cropping up, it's hard for companies to know where to invest their customer service dollars. In many ways, bots have been positioned as the answer. Many customer inquiries are routine and, in theory, could be easily (and inexpensively) handled by bots.