With the efforts of moving to sustainable and reliable energy supply, electricity markets are undergoing far-reaching changes. Due to the high-cost of failure in the real-world, it is important to test new market structures in simulation. This is the focus of the Power Trading Agent Competition (Power TAC), which proposes autonomous electricity broker agents as a means for stabilizing the electricity grid. This paper focuses on the question: how should an autonomous electricity broker agent act in competitive electricity markets to maximize its profit. We formalize the complete electricity trading problem as a continuous, high-dimensional Markov Decision Process (MDP), which is computationally intractable to solve. Our formalization provides a guideline for approximating the MDP's solution, and for extending existing solutions. We show that a previously champion broker can be viewed as approximating the solution using a lookahead policy. We present TacTex15, which improves upon this previous approximation and achieves state-of-the-art performance in competitions and controlled experiments. Using thousands of experiments against 2015 finalist brokers, we analyze TacTex15's performance and the reasons for its success. We find that lookahead policies can be effective, but their performance can be sensitive to errors in the transition function prediction, specifically demand-prediction.

The current approaches to model dynamism in DCOPs solve a sequence of static problems, reacting to the changes in the environment as the agents observe them. Such approaches, thus, ignore possible predictions on the environment evolution. To overcome such limitations, we introduce the Proactive Dynamic DCOP (PD-DCOP) model, a novel formalism to model dynamic DCOPs in the presence of exogenous uncertainty. In contrast to reactive approaches, PD-DCOPs are able to explicitly model the possible changes to the problem, and take such information into account proactively, when solving the dynamically changing problem.

Omohundro has argued that sufficiently advanced AI systems of any design would, by default, have incentives to pursue a number of instrumentally useful subgoals, such as acquiring more computing power and amassing many resources. Omohundro refers to these as “basic AI drives,” and he, along with Bostrom and others, has argued that this means great care must be taken when designing powerful autonomous systems, because even if they have harmless goals, the side effects of pursuing those goals may be quite harmful. These arguments, while intuitively compelling, are primarily philosophical. In this paper, we provide formal models that demonstrate Omohundro’s thesis, thereby putting mathematical weight behind those intuitive claims.

This paper presents a new system which provides services to elderly and persons suffering from motor or cognitive impair-ments in a smart home (SH). SH are alternative solutions in order to keep elderly and impaired persons as long as possible at their homes to allow them to live with more comfort. SH are dynamically evolving environments, thus the provided services by this system are context aware and customizable for every user. These services can be accessed by users through an application installed on a mobile device. The sys-tem uses a multi agent system (MAS) to have a dynamic and adaptive response to environmental change. Experiments are carried out in order to validate the chosen solutions.

We advocate a case-supported principle-based behavior paradigm coupled with the Fractal robot architecture as a means to control an eldercare robot. The most ethically preferable action at any given moment is determined using a principle, abstracted from cases where a consensus of ethicists exists.

As robots evolve into an integral part of the human ecosystem, humans and robots will be involved in a multitude of collaborative tasks that require complex coordination and cooperation. Indeed there has been extensive work in the robotics, planning as well as the human-robot interaction communities to understand and facilitate such seamless teaming. However, it has been argued that their increased participation as independent autonomous agents in hitherto human-habited environments has introduced many new challenges to the view of traditional human-robot teaming. When robots are deployed with independent and often self-sufficient tasks in a shared workspace, teams are often not formed explicitly and multiple teams cohabiting an environment interact more like colleagues rather than teammates. In this paper, we formalize these differences and analyze metrics to characterize autonomous behavior in such human-robot cohabitation settings.

In many situations, agents are required to use a set of strategies (behaviors) and switch among them during the course of an interaction. This work focuses on the problem of recognizing the strategy used by an agent within a small number of interactions. We propose using a Bayesian framework to address this problem. Bayesian policy reuse (BPR) has been empirically shown to be efficient at correctly detecting the best policy to use from a library in sequential decision tasks. In this paper we extend BPR to adversarial settings, in particular, to opponents that switch from one stationary strategy to another. Our proposed extension enables learning new models in an online fashion when the learning agent detects that the current policies are not performing optimally. Experiments presented in repeated games show that our approach is capable of efficiently detecting opponent strategies and reacting quickly to behavior switches, thereby yielding better performance than state-of-the-art approaches in terms of average rewards.

Human-machine systems have expanded in terms of their sensing, communication, and computational capabilities. These capabilities have led to developments of a variety of sensor systems, like robotic platforms. There are benefits to these new sensor systems, however, these benefits have been offset by new difficulties; dynamic data overload, keeping pace with changing tempo, and managing data flows from multiple sensors feeds. One approach to manage data overload from multiple sensor feeds are computational models of attention. These models also address an important aspect of human-machine symbiosis, the need for machines agents to understand attention, manage interaction based on the flow of attention, and anticipate the flow of attention in the future. Unfortunately, existing computational models of attention use assumptions that limit their applicability to human-machine systems. The Artificial Attention Architecture is introduced and demonstrates how computational models of attention can be extended to handle multi-agent, multi-sensor systems. The Artificial Attention Architecture addresses important properties of human-machine systems like the need to build symbiosis between people searching for meaning in extensive data flows and the computational algorithms processing complex and dynamic data flows.

The word symbiosis (Merriam-Webster 2015) has its origins in biology where it means “the relationship between two different kinds of living things that live together and depend on each other.” When referring to symbiotic cognitive computing, we expand this definition to include both people and intelligent computational agents who work together in a partnership (Farrell et. al 2005). Cognitive objects embody these intelligent agents, providing a physical object that may sense, compute, react, and interact with the power of cognitive computing. In this paper, we describe a few preliminary design explorations that investigate the impact of being surrounded by cognitive objects during group meetings. We frame a research agenda around the construction, programming, and usage of cognitive objects in work and home environments, and for use cases across industries such as oil and gas, healthcare and agriculture.

We present a new game-theoretic framework where Bayesian players engage in a Markov game and each has private but imperfect information regarding other players' types. Instead of utilizing Harsanyi's abstract types and a common prior distribution, we construct player types whose structure is explicit and induces a finite level belief hierarchy. We characterize equilibria in this game and formalize the computation of finding such equilibria as a constraint satisfaction problem. The effectiveness of the new framework is demonstrated on two ad hoc team work domains.