Agents.jl: a performant and feature-full agent-based modeling software of minimal code complexity

Agent-based modeling is a simulation method in which autonomous agents interact with their environment and one another, given a predefined set of rules. It is an integral method for modeling and simulating complex systems, such as socio-economic problems. Since agent-based models are not described by simple and concise mathematical equations, the code that generates them is typically complicated, large, and slow. Here we present Agents.jl, a Julia-based software that provides an ABM analysis platform with minimal code complexity. We compare our software with some of the most popular ABM software in other programming languages. We find that Agents.jl is not only the most performant but also the least complicated software, providing the same (and sometimes more) features as the competitors with less input required from the user. Agents.jl also integrates excellently with the entire Julia ecosystem, including interactive applications, differential equations, parameter optimization, and so on. This removes any “extensions library” requirement from Agents.jl, which is paramount in many other tools.

Conscious Machines for Autonomous Agents and Cybersecurity

<div>Although consciousness has been difficult to define, most researchers in artificial intelligence would agree that AI systems to date have not exhibited anything resembling consciousness. But is a conscious machine possible in the near future? I suggest that a new definition of consciousness may provide a basis for developing a conscious machine. The key is pattern recognition of correlated events in time, leading to the identification of a unified self-agent. Such a conscious system can create a simplified virtual environment, revise it to reflect updated sensor inputs, and partition the environment into self, other agents, and relevant objects. It can track recent time sequences of events, predict future events based on models and patterns in memory, and attribute causality to events and agents. It can make rapid decisions based on incomplete data, and can dynamically learn new responses based on appropriate measures of success and failure. The central aspect of consciousness is the generation of a dynamic narrative, a real-time model of a self-agent pursuing goals in a virtual reality. A conscious machine of this type may be implemented using an appropriate neural network linked to episodic memories. Near-term applications may include autonomous vehicles and online agents for cybersecurity.</div><div>Paper presented at virtual IEEE International Conference on Rebooting Computing (ICRC), Nov. 2021. To be published in conference proceedings 2022.</div>

Conscious Machines for Autonomous Agents and Cybersecurity

<div>Although consciousness has been difficult to define, most researchers in artificial intelligence would agree that AI systems to date have not exhibited anything resembling consciousness. But is a conscious machine possible in the near future? I suggest that a new definition of consciousness may provide a basis for developing a conscious machine. The key is pattern recognition of correlated events in time, leading to the identification of a unified self-agent. Such a conscious system can create a simplified virtual environment, revise it to reflect updated sensor inputs, and partition the environment into self, other agents, and relevant objects. It can track recent time sequences of events, predict future events based on models and patterns in memory, and attribute causality to events and agents. It can make rapid decisions based on incomplete data, and can dynamically learn new responses based on appropriate measures of success and failure. The central aspect of consciousness is the generation of a dynamic narrative, a real-time model of a self-agent pursuing goals in a virtual reality. A conscious machine of this type may be implemented using an appropriate neural network linked to episodic memories. Near-term applications may include autonomous vehicles and online agents for cybersecurity.</div><div>Paper presented at virtual IEEE International Conference on Rebooting Computing (ICRC), Nov. 2021. To be published in conference proceedings 2022.</div>

Enabling Artificial Intelligence Studies in Off-Road Mobility Through Physics-based Simulation of Multi-Agent Scenarios

We describe a simulation environment that enables the design and testing of control policies for off-road mobility of autonomous agents. The environment is demonstrated in conjunction with the training and assessment of a reinforcement learning policy that uses sensor fusion and inter-agent communication to enable the movement of mixed convoys of human-driven and autonomous vehicles. Policies learned on rigid terrain are shown to transfer to hard (silt-like) and soft (snow-like) deformable terrains. The environment described performs the following: multi-vehicle multibody dynamics co-simulation in a time/space-coherent infrastructure that relies on the Message Passing Interface standard for low-latency parallel computing; sensor simulation (e.g., camera, GPU, IMU); simulation of a virtual world that can be altered by the agents present in the simulation; training that uses reinforcement learning to 'teach' the autonomous vehicles to drive in an obstacle-riddled course. The software stack described is open source.

Event-driven temporal models for explanations - ETeMoX: explaining reinforcement learning

Modern software systems are increasingly expected to show higher degrees of autonomy and self-management to cope with uncertain and diverse situations. As a consequence, autonomous systems can exhibit unexpected and surprising behaviours. This is exacerbated due to the ubiquity and complexity of Artificial Intelligence (AI)-based systems. This is the case of Reinforcement Learning (RL), where autonomous agents learn through trial-and-error how to find good solutions to a problem. Thus, the underlying decision-making criteria may become opaque to users that interact with the system and who may require explanations about the system’s reasoning. Available work for eXplainable Reinforcement Learning (XRL) offers different trade-offs: e.g. for runtime explanations, the approaches are model-specific or can only analyse results after-the-fact. Different from these approaches, this paper aims to provide an online model-agnostic approach for XRL towards trustworthy and understandable AI. We present ETeMoX, an architecture based on temporal models to keep track of the decision-making processes of RL systems. In cases where the resources are limited (e.g. storage capacity or time to response), the architecture also integrates complex event processing, an event-driven approach, for detecting matches to event patterns that need to be stored, instead of keeping the entire history. The approach is applied to a mobile communications case study that uses RL for its decision-making. In order to test the generalisability of our approach, three variants of the underlying RL algorithms are used: Q-Learning, SARSA and DQN. The encouraging results show that using the proposed configurable architecture, RL developers are able to obtain explanations about the evolution of a metric, relationships between metrics, and were able to track situations of interest happening over time windows.

Measurement Noise Covariance-Adapting Kalman Filters for Varying Sensor Noise Situations

An accurate and reliable positioning system (PS) is a significant topic of research due to its broad range of aerospace applications, such as the localization of autonomous agents in GPS-denied and indoor environments. The PS discussed in this work uses ultra-wide band (UWB) sensors to provide distance measurements. UWB sensors are based on radio frequency technology and offer low power consumption, wide bandwidth, and precise ranging in the presence of nominal environmental noise. However, in practical situations, UWB sensors experience varying measurement noise due to unexpected obstacles in the environment. The localization accuracy is highly dependent on the filtering of such noise, and the extended Kalman filter (EKF) is one of the widely used techniques. In varying noise situations, where the obstacles generate larger measurement noise than nominal levels, EKF cannot offer precise results. Therefore, this work proposes two approaches based on EKF: sequential adaptive EKF and piecewise adaptive EKF. Simulation studies are conducted in static, linear, and nonlinear scenarios, and it is observed that higher accuracy is achieved by applying the proposed approaches as compared to the traditional EKF method.

Alain Ehrenberg: Autonomy and empowerment

This article considers Alain Ehrenberg's extensive analysis of individualism in contemporary France. It shows how he has traced the emergence of autonomy as a key social value, and it goes on to analyse the distinctive features of Ehrenberg's sociological approach. Unlike many of his contemporaries, Ehrenberg does not regard the growth of individualism in France as a tragic process of anomie and isolation. In fact, he is critical of what he sees as a pervasive French discourse of ‘declinology’, and he has expressed his growing frustration with this perspective more recently in explicitly political terms. Although he acknowledges that autonomy can be burdensome for individuals, he feels that the state should respond to the sociological fact of autonomy by supporting and empowering citizens as autonomous agents. The article concludes by drawing attention to the limitations of this political position.

The Ethics of Controllability as Influenceability

We present a logical analysis of influence and control over the actions of others, and address consequential causal and normative responsibilities. We first account for the way in which influence can be exercised over the behaviour of autonomous agents. On this basis we determine the conditions under which influence leads to control on the implementation of positive and negative values. We finally define notions of causal and normative responsibility for the action of others. Our logical framework is based on STIT logic and is complemented with a series of examples illustrating the application. Our analysis applies to interactions between humans as well as to those involving autonomous artificial agents.