Multiagent Model of Rail-Road Intersection with Connected Vehicles

The multiagent approach to modelling, traditionally dedicated for distributed systems, can be applied on any platform where there are more processes or control threads. The world of surface transport is a typical example of such a situation where high numbers of dynamic entities (agents) interacting with each other represent a complex problem to solve, analyse and visualise. The main focus of this paper is on functional description of the traffic control problem at the rail-road intersection. Unlike conventional approaches, this model assumes usage of modern (infrastructure-to-vehicle, vehicle-to-vehicle) communication technologies as an essential base of cooperative intelligent transportation systems. The authors use the development toolkit NetLogo, explaining step-by-step the key programming details, to get a comprehensive overview of the operation of the entire system through simple definitions of a number of simple cooperating agents. The introduced model is implementation free and shows newly offered functionalities on the principal level, while a minimum theory of collective intelligence hidden in the background is needed.

Scientific multi-agent reinforcement learning for wall-models of turbulent flows

The predictive capabilities of turbulent flow simulations, critical for aerodynamic design and weather prediction, hinge on the choice of turbulence models. The abundance of data from experiments and simulations and the advent of machine learning have provided a boost to these modeling efforts. However, simulations of turbulent flows remain hindered by the inability of heuristics and supervised learning to model the near-wall dynamics. We address this challenge by introducing scientific multi-agent reinforcement learning (SciMARL) for the discovery of wall models for large-eddy simulations (LES). In SciMARL, discretization points act also as cooperating agents that learn to supply the LES closure model. The agents self-learn using limited data and generalise to extreme Reynolds numbers and previously unseen geometries. The present simulations reduce by several orders of magnitude the computational cost over fully-resolved simulations, while reproducing key flow quantities. We believe that SciMARL creates new capabilities for the simulation of turbulent flows.

Dynamic Multiagent Incentive Contracts: Existence, Uniqueness, and Implementation

Multiagent incentive contracts are advanced techniques for solving decentralized decision-making problems with asymmetric information. The principal designs contracts aiming to incentivize non-cooperating agents to act in his or her interest. Due to the asymmetric information, the principal must balance the efficiency loss and the security for keeping the agents. We prove both the existence conditions for optimality and the uniqueness conditions for computational tractability. The coupled principal-agent problems are converted to solving a Hamilton–Jacobi–Bellman equation with equilibrium constraints. Extending the incentive contract to a multiagent setting with history-dependent terminal conditions opens the door to new applications in corporate finance, institutional design, and operations research.

Pooling Risk Games

There are numerous situations in which variability reduction is desirable. We examine cases where such reductions can be achieved by cooperating agents who share similar interests. Our goal is to quantify the contribution of each of the agents toward this reduction. We model this situation as a cooperative game in which the cost is defined as the minimal standard deviation the cooperating agents can achieve. We show that this game is subadditive and has a nonempty core. We derive special presentations for the Shapley and Banzhaf values.

A Coupled Operational Semantics for Goals and Commitments

Commitments capture how an agent relates to another agent, whereas goals describe states of the world that an agent is motivated to bring about. Commitments are elements of the social state of a set of agents whereas goals are elements of the private states of individual agents. It makes intuitive sense that goals and commitments are understood as being complementary to each other. More importantly, an agent's goals and commitments ought to be coherent, in the sense that an agent's goals would lead it to adopt or modify relevant commitments and an agent's commitments would lead it to adopt or modify relevant goals. However, despite the intuitive naturalness of the above connections, they have not been adequately studied in a formal framework. This article provides a combined operational semantics for goals and commitments by relating their respective life cycles as a basis for how these concepts (1) cohere for an individual agent and (2) engender cooperation among agents. Our semantics yields important desirable properties of convergence of the configurations of cooperating agents, thereby delineating some theoretically well-founded yet practical modes of cooperation in a multiagent system.

Cooperation in collective systems

Cooperative collective systems, such as social insects, display amazing behaviors that combine efficiency, flexibility, and robustness. This chapter on cooperation in collective systems illustrates a fundamental property of natural organisms which operate only occasionally in isolation. The chapter discusses the methods that can be used to synthesize colonies or swarms of cooperating agents and some of the key principles that characterize such types of system such as coordination, generalization, and self-organization. It focuses in particular on collective evolutionary robotics approaches in which swarm of robots are evolved for the ability to solve problems that require cooperation.