Innovation diffusion has been studied extensively in a variety of disciplines, including sociology, economics, marketing, ecology, and computer science. Traditional literature on innovation diffusion has been dominated by models of aggregate behavior and trends. However, the agent-based modeling (ABM) paradigm is gaining popularity as it captures agent heterogeneity and enables fine-grained modeling of interactions mediated by social and geographic networks. While most ABM work on innovation diffusion is theoretical, empirically grounded models are increasingly important, particularly in guiding policy decisions. We present a critical review of empirically grounded agent-based models of innovation diffusion, developing a categorization of this research based on types of agent models as well as applications. By connecting the modeling methodologies in the fields of information and innovation diffusion, we suggest that the maximum likelihood estimation framework widely used in the former is a promising paradigm for calibration of agent-based models for innovation diffusion. Although many advances have been made to standardize ABM methodology, we identify four major issues in model calibration and validation, and suggest potential solutions.

A computer algorithm equipped with a form of artificial curiosity can learn to solve tricky problems even when it isn't immediately clear what actions might help it reach this goal. Researchers at the University of California, Berkeley, developed an "intrinsic curiosity model" to make their learning algorithm work even when there isn't a strong feedback signal. The curiosity model developed by this team sees the AI software controlling a virtual agent in a video game seek to maximize its understanding of its environment and especially aspects of that environment that affect it. There have been previous efforts to give AI agents curiosity, but these have tended to work in a more simplistic way. The trick may help address a shortcoming of today's most powerful machine-learning techniques, and it could point to ways of making machines better at solving real-world problems.

In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part of their learning process, agents may link these interruptions, that impact their reward, to specific states and deliberately avoid them. The situation is particularly challenging in a multi-agent context because agents might not only learn from their own past interruptions, but also from those of other agents. Orseau and Armstrong defined \emph{safe interruptibility} for one learner, but their work does not naturally extend to multi-agent systems. This paper introduces \textit{dynamic safe interruptibility}, an alternative definition more suited to decentralized learning problems, and studies this notion in two learning frameworks: \textit{joint action learners} and \textit{independent learners}. We give realistic sufficient conditions on the learning algorithm to enable dynamic safe interruptibility in the case of joint action learners, yet show that these conditions are not sufficient for independent learners. We show however that if agents can detect interruptions, it is possible to prune the observations to ensure dynamic safe interruptibility even for independent learners.

We consider abstract-argumentation-theoretic coalition formability in this work. Taking a model from political alliance among political parties, we will contemplate profitability, and then formability, of a coalition. As is commonly understood, a group forms a coalition with another group for a greater good, the goodness measured against some criteria. As is also commonly understood, however, a coalition may deliver benefits to a group X at the sacrifice of something that X was able to do before coalition formation, which X may be no longer able to do under the coalition. Use of the typical conflict-free sets of arguments is not very fitting for accommodating this aspect of coalition, which prompts us to turn to a weaker notion, conflict-eliminability, as a property that a set of arguments should primarily satisfy. We require numerical quantification of attack strengths as well as of argument strengths for its characterisation. We will first analyse semantics of profitability of a given conflict-eliminable set forming a coalition with another conflict-eliminable set, and will then provide four coalition formability semantics, each of which formalises certain utility postulate(s) taking the coalition profitability into account.

This paper proposes three different distributed event-triggered control algorithms to achieve leader-follower consensus for a network of Euler-Lagrange agents. We firstly propose two model-independent algorithms for a subclass of Euler-Lagrange agents without the vector of gravitational potential forces. By model-independent, we mean that each agent can execute its algorithm with no knowledge of the agent self-dynamics. A variable-gain algorithm is employed when the sensing graph is undirected; algorithm parameters are selected in a fully distributed manner with much greater flexibility compared to all previous work concerning event-triggered consensus problems. When the sensing graph is directed, a constant-gain algorithm is employed. The control gains must be centrally designed to exceed several lower bounding inequalities which require limited knowledge of bounds on the matrices describing the agent dynamics, bounds on network topology information and bounds on the initial conditions. When the Euler-Lagrange agents have dynamics which include the vector of gravitational potential forces, an adaptive algorithm is proposed which requires more information about the agent dynamics but can estimate uncertain agent parameters. For each algorithm, a trigger function is proposed to govern the event update times. At each event, the controller is updated, which ensures that the control input is piecewise constant and saves energy resources. We analyse each controllers and trigger function and exclude Zeno behaviour. Extensive simulations show 1) the advantages of our proposed trigger function as compared to those in existing literature, and 2) the effectiveness of our proposed controllers.

In this work, we present a methodology that enables an agent to make efficient use of its exploratory actions by autonomously identifying possible objectives in its environment and learning them in parallel. The identification of objectives is achieved using an online and unsupervised adaptive clustering algorithm. The identified objectives are learned (at least partially) in parallel using Q-learning. Using a simulated agent and environment, it is shown that the converged or partially converged value function weights resulting from off-policy learning can be used to accumulate knowledge about multiple objectives without any additional exploration. We claim that the proposed approach could be useful in scenarios where the objectives are initially unknown or in real world scenarios where exploration is typically a time and energy intensive process. The implications and possible extensions of this work are also briefly discussed.

In this work, we investigate how the order in which tasks are considered to be acted upon by probabilistic agents with time-variant response thresholds within a fully decentralized multiagent system may affect task allocation, task fulfillment levels, specialization tendencies, and system robustness. The tested ordering schemas are: (1) ascending subjective action threshold, (2) descending objective task stimulus, (3) descending action probability P as defined by Theraulaz, Bonabeau, and Deneubourg (1998) which combines both subjective threshold and objective stimulus, and (4) a random ordering to serve as a baseline for comparison. As the behavior of real-world systems tends to stem from complex interactions of multiple system aspects, we expand our analysis by further breaking down each of these ordering approaches into positive vs. negative reinforcement under different learning and forgetting rates for updating agent response thresholds.

This paper explores how an autonomous agent can model dynamic environments and use that knowledge to improve its behavior. This capability is of particular importance for persistent agents, or long-term autonomy. Inspiration is drawn from circadian rhythms in nature, which drive periodic behavior in many organisms. In our approach, the chemical oscillators from nature are replaced with methods from time series analysis designed for forecasting complex season patterns. This model is incorporated into a behavior-based architecture as an advanced-percept, providing future estimates of the environment rather than current measurements. A simulated application of a janitor robot working in an environment with heavy pedestrian traffic was created as a testbed. Experimental data used real world pedestrian traffic counts and showed an agent using online forecasting of future traffic outperformed both a reactive, sensor-based, strategy and a strategy with a deterministic schedule.

We propose a logic of asynchronous announcements, where truthful announcements are publicly sent but individually received by agents. Additional to epistemic modalities, the logic therefore contains two types of dynamic modalities, for sending messages and for receiving messages. The semantics defines truth relative to the current state of reception of messages for all agents. This means that knowledge need not be truthful, because some messages may not have been received by the knowing agent. Messages that are announcements may also result in partial synchronization, namely when an agent learns from receiving an announcement that other announcements must already have been received by other agents. We give detailed examples of the semantics, and prove several semantic results, including that: after an announcement an agent knows that a proposition is true, if and only if on condition of the truth of that announcement, the agent knows that after that announcement and after any number of other agents also receiving it, the proposition is true. We show that on multi-agent epistemic models, each formula in asynchronous announcement logic is equivalent to a formula in epistemic logic.

Swarm robotics has experienced a rapid expansion in recent years, primarily fueled by specialized multi-robot systems developed to achieve dedicated collective actions. These specialized platforms are in general designed with swarming considerations at the front and center. Key hardware and software elements required for swarming are often deeply embedded and integrated with the particular system. However, given the noticeable increase in the number of low-cost mobile robots readily available, practitioners and hobbyists may start considering to assemble full-fledged swarms by minimally retrofitting such mobile platforms with a swarm-enabling technology. Here, we report one possible embodiment of such a technology designed to enable the assembly and the study of swarming in a range of general-purpose robotic systems. This is achieved by combining a modular and transferable software toolbox with a hardware suite composed of a collection of low-cost and off-the-shelf components. The developed technology can be ported to a relatively vast range of robotic platforms with minimal changes and high levels of scalability. This swarm-enabling technology has successfully been implemented on two distinct distributed multi-robot systems, a swarm of mobile marine buoys and a team of commercial terrestrial robots. We have tested the effectiveness of both of these distributed robotic systems in performing collective exploration and search scenarios, as well as other classical cooperative behaviors. Experimental results on different swarm behaviors are reported for the two platforms in uncontrolled environments and without any supporting infrastructure. The design of the associated software library allows for a seamless switch to other cooperative behaviors, and also offers the possibility to simulate newly designed collective behaviors prior to their implementation onto the platforms.