scholarly journals Agent-based Evolutionary and Memetic Black-box Discrete Optimization

2017 ◽  
Vol 108 ◽  
pp. 907-916 ◽  
Author(s):  
Michal Kowol ◽  
Kamil Pietak ◽  
Marek Kisiel-Dorohinicki ◽  
Aleksander Byrski
Keyword(s):  
Discrete Optimization ◽  
Black Box ◽  
Agent Based

scholarly journals Black-Box-Based Mathematical Modelling of Machine Intelligence Measuring

Mathematics ◽  
2021 ◽  
Vol 9 (6) ◽  
pp. 681
Author(s):  
László Barna Iantovics
Keyword(s):  
Problem Solving ◽  
Scientific Literature ◽  
Real Life ◽  
Intelligent Agent ◽  
Difficult Problem ◽  
Black Box ◽  
Machine Intelligence ◽  
Agent Based ◽  
Np Hard Problem ◽  
Box Method

Current machine intelligence metrics rely on a different philosophy, hindering their effective comparison. There is no standardization of what is machine intelligence and what should be measured to quantify it. In this study, we investigate the measurement of intelligence from the viewpoint of real-life difficult-problem-solving abilities, and we highlight the importance of being able to make accurate and robust comparisons between multiple cooperative multiagent systems (CMASs) using a novel metric. A recent metric presented in the scientific literature, called MetrIntPair, is capable of comparing the intelligence of only two CMASs at an application. In this paper, we propose a generalization of that metric called MetrIntPairII. MetrIntPairII is based on pairwise problem-solving intelligence comparisons (for the same problem, the problem-solving intelligence of the studied CMASs is evaluated experimentally in pairs). The pairwise intelligence comparison is proposed to decrease the necessary number of experimental intelligence measurements. MetrIntPairII has the same properties as MetrIntPair, with the main advantage that it can be applied to any number of CMASs conserving the accuracy of the comparison, while it exhibits enhanced robustness. An important property of the proposed metric is the universality, as it can be applied as a black-box method to intelligent agent-based systems (IABSs) generally, not depending on the aspect of IABS architecture. To demonstrate the effectiveness of the MetrIntPairII metric, we provide a representative experimental study, comparing the intelligence of several CMASs composed of agents specialized in solving an NP-hard problem.

scholarly journals Modeling the Spread and Control of COVID-19

Systems ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 53
Author(s):  
Ashutosh Trivedi ◽  
Nanda Kishore Sreenivas ◽  
Shrisha Rao
Keyword(s):  
Herd Immunity ◽  
Black Box ◽  
Personal Hygiene ◽  
Confined Space ◽  
Real Situation ◽  
Seir Model ◽  
Agent Based ◽  
Social Distancing ◽  
The Difference ◽  
And Control

Data-centric models of COVID-19 have been attempted, but have certain limitations. In this work, we propose an agent-based model of the epidemic in a confined space of agents representing humans. An extension to the SEIR model allows us to consider the difference between the appearance (black-box view) of the spread of disease and the real situation (glass-box view). Our model allows for simulations of lockdowns, social distancing, personal hygiene, quarantine, and hospitalization, with further considerations of different parameters, such as the extent to which hygiene and social distancing are observed in a population. Our results provide qualitative indications of the effects of various policies and parameters, for instance, that lockdowns by themselves are extremely unlikely to bring an end to an epidemic and may indeed make things worse, that social distancing is more important than personal hygiene, and that the growth of infection is significantly reduced for moderately high levels of social distancing and hygiene, even in the absence of herd immunity.

scholarly journals MULTIAGENT LEARNING FOR BLACK BOX SYSTEM REWARD FUNCTIONS

2009 ◽  
Vol 12 (04n05) ◽  
pp. 475-492 ◽  
Author(s):  
KAGAN TUMER ◽  
ADRIAN AGOGINO
Keyword(s):  
Global Solutions ◽  
Analytical Form ◽  
Black Box ◽  
Management Problem ◽  
Credit Assignment ◽  
Air Traffic Flow Management ◽  
Agent Based ◽  
Team Games ◽  
Traffic Flow Management ◽  
Reward Functions

In large, distributed systems composed of adaptive and interactive components (agents), ensuring the coordination among the agents so that the system achieves certain performance objectives is a challenging proposition. The key difficulty to overcome in such systems is one of credit assignment: How to apportion credit (or blame) to a particular agent based on the performance of the entire system. In this paper, we show how this problem can be solved in general for a large class of reward functions whose analytical form may be unknown (hence "black box" reward). This method combines the salient features of global solutions (e.g. "team games") which are broadly applicable but provide poor solutions in large problems with those of local solutions (e.g. "difference rewards") which learn quickly, but can be computationally burdensome. We introduce two estimates for local rewards for a class of problems where the mapping from the agent actions to system reward functions can be decomposed into a linear combination of nonlinear functions of the agents' actions. We test our method's performance on a distributed marketing problem and an air traffic flow management problem and show a 44% performance improvement over team games and a speedup of order n for difference rewards (for an n agent system).

scholarly journals Modeling the Spread and Control of COVID-19

2020 ◽  
Author(s):  
Ashutosh Trivedi ◽  
Nanda Kishore Sreenivas ◽  
Shrisha Rao
Keyword(s):  
Herd Immunity ◽  
Black Box ◽  
Personal Hygiene ◽  
Confined Space ◽  
Real Situation ◽  
Seir Model ◽  
Agent Based ◽  
Social Distancing ◽  
The Difference ◽  
And Control

ABSTRACTData-centric models of COVID-19 have been tried, but have certain limitations. In this work, we propose an agent-based model of the epidemic in a confined space of agents representing humans. An extension to the SEIR model allows us to consider the difference between the appearance (black-box view) of the spread of disease, and the real situation (glass-box view). Our model allows for simulations of lockdowns, social distancing, personal hygiene, quarantine, and hospitalization, with further considerations of different parameters such as the extent to which hygiene and social distancing are observed in a population. Our results give qualitative indications of the effects of various policies and parameters; for instance, that lockdowns by themselves are extremely unlikely to bring an end to an epidemic and may indeed make things worse, that social distancing matters more than personal hygiene, and that the growth of infection comes down significantly for moderately high levels of social distancing and hygiene, even in the absence of herd immunity.

Analytical Sociology and Agent-Based Modeling: Is Generative Sufficiency Sufficient?

2017 ◽  
Vol 35 (3) ◽  
pp. 157-178 ◽  
Author(s):  
Francisco J. León-Medina
Keyword(s):  
Computer Modeling ◽  
Black Box ◽  
Agent Based Modeling ◽  
Agent Based ◽  
Generative Process ◽  
Current Definition ◽  
Analytical Sociology ◽  
Modeling Practices ◽  
Definition Of

Building mechanisms-based, black box–free explanations is the main goal of analytical sociology. In this article, I offer some reasons to question whether some of the conceptual and methodological developments of the analytical community really serve this goal. Specifically, I argue that grounding our computer modeling practices in the current definition of mechanisms posits a serious risk of defining an ideal-typical research path that neglects the role that the understanding of the generative process must have for a black box–free explanation to be met. I propose some conceptual and methodological alternatives, and I identify some collective challenges that the analytical community should tackle in order not to deviate from its main goal.

scholarly journals A numerical method for the approximation of stable and unstable manifolds of microscopic simulators

2021 ◽  
Author(s):  
Constantinos Siettos ◽  
Lucia Russo
Keyword(s):  
Closed Form ◽  
Large Scale ◽  
Stochastic Systems ◽  
Black Box ◽  
Coarse Grained ◽  
Stationary States ◽  
Macroscopic Description ◽  
Stable And Unstable Manifolds ◽  
Agent Based ◽  
Unstable Manifolds

AbstractWe address a numerical methodology for the approximation of coarse-grained stable and unstable manifolds of saddle equilibria/stationary states of multiscale/stochastic systems for which a macroscopic description does not exist analytically in a closed form. Thus, the underlying hypothesis is that we have a detailed microscopic simulator (Monte Carlo, molecular dynamics, agent-based model etc.) that describes the dynamics of the subunits of a complex system (or a black-box large-scale simulator) but we do not have explicitly available a dynamical model in a closed form that describes the emergent coarse-grained/macroscopic dynamics. Our numerical scheme is based on the equation-free multiscale framework, and it is a three-tier procedure including (a) the convergence on the coarse-grained saddle equilibrium, (b) its coarse-grained stability analysis, and (c) the approximation of the local invariant stable and unstable manifolds; the later task is achieved by the numerical solution of a set of homological/functional equations for the coefficients of a polynomial approximation of the manifolds.

Sign in / Sign up

Export Citation Format

Share Document