Multi-agent Artificial Intelligence Research Articles

Generating intelligent agent behaviors in multi-agent game AI using deep reinforcement learning algorithm

<span>The utilization of games in training the reinforcement learning (RL) agent is to describe the complex and high-dimensional real-world data. By utilizing games, RL researchers will be able to evade high experimental costs in training an agent to do intelligence tasks. The objective of this research is to generate intelligent agent behaviors in multi-agent game artificial intelligence (AI) using deep reinforcement learning (DRL) algorithm. A basic RL algorithm called deep Q network is chosen to be implemented. The agent is trained by the environment's raw pixel images and the action list information. The experiments conducted by using this algorithm show the agent’s decision-making ability in choosing a favorable action. In the default setting for the algorithm, the training is set into 1 epoch and 0.0025 learning rate. The number of training iterations is set to one as the training function will be repeatedly called for every 4-timestep. However, the author also experimented with two different scenarios in training the agent and compared the results. The experimental findings demonstrate that our agents learn correctly and successfully while actively participating in the game in real time. Additionally, our agent can quickly adjust against a different enemy on a varied map because of the observed knowledge from prior training.</span>

What is the simplest model that can account for high-fidelity imitation?

What inductive biases must be incorporated into multi-agent artificial intelligence models to get them to capture high-fidelity imitation? We think very little is needed. In the right environments, both instrumental- and ritual-stance imitation can emerge from generic learning mechanisms operating on non-deliberative decision architectures. In this view, imitation emerges from trial-and-error learning and does not require explicit deliberation.

Progress in simulating human geography: Assemblage theory and the practice of multi-agent artificial intelligence modeling

Over the last few years, there has been an explosion of interest in assemblage theory among human geographers. During this same period, a growing number of scholars in the field have utilized computational methodologies to simulate the complex adaptive systems they study. However, very little attention has been paid to the connections between these two developments. This article outlines those connections and argues that more explicitly integrating assemblage theory and computer modeling can encourage a more robust philosophical understanding of both and facilitate progress in scientific research on the ways in which complex socio-material systems form and transform.

Management of virtual organizations based on multi-agent systems

The emergence of new forms of business organization due to the development of the latest information technologies leads to the need to find adequate ways to manage virtual structures. This article discusses the features of multi-agent artificial intelligence systems and the possibilities of their application in virtual organizations. The concept of a multi-agent system is proposed, which will improve the management processes of a virtual organization. The developed algorithm is adaptive and can be used in various virtual organizations for self-development of their management systems and achieving their goals.

Computational Science of Religion

This article provides a basic overview of the most common methods of computer modelling and simulation that are currently being used to study religion. It focuses on the use (and illustrates the value) of system dynamics models, agent-based models, including game theory and multi-agent artificial intelligence models, and artificial neural networks. General use case examples are provided, and considerations for future research are discussed. We conclude by encouraging scholars interested in religion and related fields to incorporate techniques from the computational science of religion into their collaborative methodological toolkits.

Minding morality: ethical artificial societies for public policy modeling

Public policies are designed to have an impact on particular societies, yet policy-oriented computer models and simulations often focus more on articulating the policies to be applied than on realistically rendering the cultural dynamics of the target society. This approach can lead to policy assessments that ignore crucial social contextual factors. For example, by leaving out distinctive moral and normative dimensions of cultural contexts in artificial societies, estimations of downstream policy effectiveness fail to account for dynamics that are fundamental in human life and central to many public policy challenges. In this paper, we supply evidence that incorporating morally salient dimensions of a culture is critically important for producing relevant and accurate evaluations of social policy when using multi-agent artificial intelligence models and simulations.

Oscillatory evolution of collective behavior in evolutionary games played with reinforcement learning

Large-scale cooperation underpins the evolution of ecosystems and the human society, and the collective behaviors by self-organization of multi-agent systems are the key for understanding. As artificial intelligence (AI) prevails in almost all branches of science, it would be of great interest to see what new insights of collective behaviors could be obtained from a multi-agent AI system. Here, we introduce a typical reinforcement learning (RL) algorithm—Q-learning into evolutionary game dynamics, where agents pursue optimal action on the basis of the introspectiveness rather than the outward manner such as the birth–death or imitation processes in the traditional evolutionary game (EG). We investigate the cooperation prevalence numerically for a general $$2\times 2$$ game setting. We find that the cooperation prevalence in the multi-agent AI is unexpectedly of equal level as in the traditional EG in most cases. However, in the snowdrift games with RL, we reveal that explosive cooperation appears in the form of periodic oscillation, and we study the impact of the payoff structure on its emergence. Finally, we show that the periodic oscillation can also be observed in some other EGs with the RL algorithm, such as the rock–paper–scissors game. Our results offer a reference point to understand the emergence of cooperation and oscillatory behaviors in nature and society from AI’s perspective.

Multiparty Dynamics and Failure Modes for Machine Learning and Artificial Intelligence

An important challenge for safety in machine learning and artificial intelligence systems is a set of related failures involving specification gaming, reward hacking, fragility to distributional shifts, and Goodhart’s or Campbell’s law. This paper presents additional failure modes for interactions within multi-agent systems that are closely related. These multi-agent failure modes are more complex, more problematic, and less well understood than the single-agent case, and are also already occurring, largely unnoticed. After motivating the discussion with examples from poker-playing artificial intelligence (AI), the paper explains why these failure modes are in some senses unavoidable. Following this, the paper categorizes failure modes, provides definitions, and cites examples for each of the modes: accidental steering, coordination failures, adversarial misalignment, input spoofing and filtering, and goal co-option or direct hacking. The paper then discusses how extant literature on multi-agent AI fails to address these failure modes, and identifies work which may be useful for the mitigation of these failure modes.

Collective behavior of artificial intelligence population: transition from optimization to game

Collective behavior in the resource allocation systems has attracted much attention, where the efficiency of the system is intimately depended on the self-organized processes of the multiple agents that composed the system. Nowadays, as artificial intelligence (AI) is adopted ubiquitously in decision making in various scenes, it becomes crucial and unavoidable to understand what would emerge in an multi-agent AI systems for resource allocation and how can we intervene the collective behavior there in the future, as we have experience of the possible unexpected outcomes that are induced by collective behavior. Here, we introduce the reinforcement learning (RL) algorithm into minority game (MG) dynamics, in which agents have learning ability based on one typical RL scheme, Q-learning. We investigate the dynamical behaviors of the system numerically and analytically for a different game setting, with combination of two different types of agents which mimic the diversified situations. It is found that through short-term training, the multi-agent AI system adopting Q-learning algorithm relaxes to the optimal solution of the game. Moreover, one striking phenomenon is the transition of interaction mechanism from self-organized optimization to game through tuning the fraction of RL agents $$\eta _{q}$$ . The critical curve for transition between the two mechanisms in phase diagram is obtained analytically. The adaptability of the AI agents population against the time-variable environment is also discussed. To gain further understanding of these phenomena, a theoretical framework with mean-field approximation is also developed. Our findings from the simplified multi-agent AI system may give new enlightenment to how the reconciliation and optimization can be breed in the coming era of AI.

Psychological Perspectives on Intentional Forgetting: An Overview of Concepts and Literature

Concepts and mechanisms of forgetting are a subject of great interest in today’s digital world. Especially for the development of socio-digital systems utilizing artificial intelligence (AI), the question arises how to deal with growing amounts of information. Psychological models of forgetting offer numerous theoretical perspectives that can be transferred to AI research and practice. This article presents a short terminological overview and systematic of psychological concepts of forgetting from an individual, group, and organizational level. These views at the micro-, meso-, and macro-level may stimulate interdisciplinary research and offer models of intentional forgetting for single and multi-agent AI systems.

Multi-Agent Planning for Automatic Geospatial Web Service Composition in Geoportals

Automatic composition of geospatial web services increases the possibility of taking full advantage of spatial data and processing capabilities that have been published over the internet. In this paper, a multi-agent artificial intelligence (AI) planning solution was proposed, which works within the geoportal architecture and enables the geoportal to compose semantically annotated Open Geospatial Consortium (OGC) Web Services based on users’ requirements. In this solution, the registered Catalogue Service for Web (CSW) services in the geoportal along with a composition coordinator component interact together to synthesize Open Geospatial Consortium Web Services (OWSs) and generate the composition workflow. A prototype geoportal was developed, a case study of evacuation sheltering was implemented to illustrate the functionality of the algorithm, and a simulation environment, including one hundred simulated OWSs and five CSW services, was used to test the performance of the solution in a more complex circumstance. The prototype geoportal was able to generate the composite web service, based on the requested goals of the user. Additionally, in the simulation environment, while the execution time of the composition with two CSW service nodes was 20 s, the addition of new CSW nodes reduced the composition time exponentially, so that with five CSW nodes the execution time reduced to 0.3 s. Results showed that due to the utilization of the computational power of CSW services, the solution was fast, horizontally scalable, and less vulnerable to the exponential growth in the search space of the AI planning problem.

Can we predict religious extremism?

ABSTRACTGiven events such as 11 September, the 2013 Boston Bombing, and the 2015 Paris attacks it is becoming increasingly apparent that religious extremism has great potential to negatively impact our daily lives. Predicting religious extremism could – in principle – allow us to respond to, mediate, or eliminate threats more efficiently. It is argued here that predicting religious extremism is possible but religious systems are complex dynamic systems and should be addressed as such. To address religious systems in a way that could provide useful predictions, one should use multi-agent artificial intelligence models that are validated using empirical studies of human cognition to define rules for the agents and historical and contemporary data sources (ex. “big-data” and historical databases) to calibrate and parameterize simulations. Ultimately, I conclude that near-term prediction is possible if one incorporates social and biological environments as well as inter- and intra-agent cognitive mechanisms, but long term predictions would be unreliable. Key to this approach is the admission that cognitive mechanisms play crucial roles in the generation and transmission of culture as well as the recognition that social and biological environments provide input to these mechanisms but neither social or biological environmental input is sufficient by itself.

Method, Theory, and Multi-Agent Artificial Intelligence

The construction of computer models is becoming an increasingly useful and popular way of testing theories in the cognitive sciences. This paper will present a brief overview of the methods available for constructing and testing computer models of social phenomena such as religious beliefs and behaviors. It will focus on the importance of theoretical continuity and data replication in computer modelling while negotiating the relationship between specificity and ecological validity when models are extended into novel contexts. This paper will argue that computer modeling is an important supplement to the methodological toolbox of cognitive scientists interested in human social phenomena. However, this is only the case if developers pay close attention to research methods and theories and if the method of a model’s development is appropriate for the target phenomenon (Sun, 2006). It concludes that multi-agent AI models are the most appropriate computational tool for the study of complex social phenomena.

Multi-Agent Augmented Computer Vision Technologies to Support Human Monitoring of Secure Computing Facilities

Humans are poorly equipped to perform repetitive tasks without adversely affecting the efficiency with which they are performing the task. One such task is the monitoring of CCTV footage to prevent the theft of, or tampering with, computing equipment. This paper introduces an approach towards security monitoring that uses a Computer Vision augmented with Speeded-Up Robust Features (SURF) as the catalyst to provide event-driven object detection to assist in securing an environment. A multi-agent artificial intelligence is used to improve the processing of event detection during the execution of these computer vision algorithms. The scenario of a secure computer environment is used to demonstrate the problems with current approaches and present an alternative to human monitoring using Computer Vision. The paper demonstrates that some of the physical aspects of information security can be improved through the use of SURF algorithms.

A Continuation Method for Nash Equilibria in Structured Games

Structured game representations have recently attracted interest as models for multi-agent artificial intelligence scenarios, with rational behavior most commonly characterized by Nash equilibria. This paper presents efficient, exact algorithms for computing Nash equilibria in structured game representations, including both graphical games and multi-agent influence diagrams (MAIDs). The algorithms are derived from a continuation method for normal-form and extensive-form games due to Govindan and Wilson; they follow a trajectory through a space of perturbed games and their equilibria, exploiting game structure through fast computation of the Jacobian of the payoff function. They are theoretically guaranteed to find at least one equilibrium of the game, and may find more. Our approach provides the first efficient algorithm for computing exact equilibria in graphical games with arbitrary topology, and the first algorithm to exploit fine-grained structural properties of MAIDs. Experimental results are presented demonstrating the effectiveness of the algorithms and comparing them to predecessors. The running time of the graphical game algorithm is similar to, and often better than, the running time of previous approximate algorithms. The algorithm for MAIDs can effectively solve games that are much larger than those solvable by previous methods.

Multiagent AI implementations an emerging software engineering trend

A model is presented for the design and implementation of software systems using multiagent artificial intelligence (AI) and concurrent software engineering techniques. The stages of conceptualization, design and implementation are defined by AI methods. It is proposed that software systems be designed through knowledge acquisition, specification, and multiagent implementations. Multiagent implementations are proposed here to facilitate a fault-tolerant software-design methodology, applying recent research that has led to fault-tolerant AI systems. A particular approach to, and an AI formulation for designing fault-free and fault-tolerant software is presented, based on the agent models of computation. An approach using object-oriented design, coupled with a novel multi-kernel approach, is presented. A system is defined by many communicating pairs of kernels, each defining a part of the system, as specified by object-level knowledge acquisition. An overview of agent morphisms and algebras is presented and applied to the design.