scholarly journals Interactive Learning and Decision Making: Foundations, Insights & Challenges

Author(s):  
Frans A. Oliehoek

Designing "teams of intelligent agents that successfully coordinate and learn about their complex environments inhabited by other agents (such as humans)" is one of the major goals of AI, and it is the challenge that I aim to address in my research. In this paper I give an overview of some of the foundations, insights and challenges in this field of Interactive Learning and Decision Making.

2018 ◽  
Author(s):  
Alexander Rich ◽  
Todd Matthew Gureckis

Learning usually improves the accuracy of beliefs through the accumulation of experience. But are there limits to learning that prevent us from accurately understanding our world? In this paper we investigate the concept of a “learning trap”—the formation of a stable false belief even with extensive experience. Our review highlights how these traps develop though the interaction of learning and decision making in unknown environments. We further document a particularly pernicious learning trap driven by selective attention, a mechanism often assumed to facilitate learning in complex environments. Using computer simulation we demonstrate the key attributes of the agent and environment that lead to this new type of learning trap. Then, in a series of experiments we present evidence that people robustly fall into this trap, even in the presence of various interventions predicted to meliorate it. These results highlight a fundamental limit to learning and adaptive behavior that impacts individuals, organizations, animals, and machines.


2014 ◽  
Vol Volume 2 ◽  
Author(s):  
Hasmik Atoyan ◽  
Jean-Marc Robert ◽  
Jean-Rémi Duquet

The utilization of Decision Support Systems (DSS) in complex dynamic environments leads the human operator almost inevitably to having to face several types of uncertainties. Thus it is essential for system designers to clearly understand the different types of uncertainties that could exist in human-machine systems of complex environments, to know their impacts on the operator's trust in the systems and decision-making process, and to have guidelines on how to present uncertain information on user interfaces. It is also essential for them to have an overview of the different stages, levels, and types of system automation, and to know their possible impacts on the creation of different types of uncertainties. This paper investigates these topics and aim at helping researchers and practitioners to deal with uncertainties in complex environments.


2014 ◽  
Vol 27 (2) ◽  
pp. 901-912 ◽  
Author(s):  
José M. Merigó ◽  
Marta Peris-Ortiz ◽  
Daniel Palacios-Marqués

2011 ◽  
pp. 857-866 ◽  
Author(s):  
Gloria E Phillips-Wren

Internet-based, distributed systems have become essential in modern organizations. When combined with artificial intelligence (AI) techniques such as intelligent agents, such systems can become powerful aids to decision makers. These newer intelligent systems have extended the scope of traditional decision support systems (DSSs) to assist users with real-time decision making, multiple information flows, dynamic data, information overload, time-pressured decisions, inaccurate data, difficult-to-access data, distributed decision making, and highly uncertain decision environments. As a class, they are called intelligent decision support systems (IDSSs).


10.5772/5796 ◽  
2005 ◽  
Vol 2 (2) ◽  
pp. 12 ◽  
Author(s):  
Alborz Geramifard ◽  
Peyman Nayeri ◽  
Reza Zamani-Nasab ◽  
Jafar Habibi

This paper presents a new architecture called FAIS for implementing intelligent agents cooperating in a special Multi Agent environment, namely the RoboCup Rescue Simulation System. This is a layered architecture which is customized for solving fire extinguishing problem. Structural decision making algorithms are combined with heuristic ones in this model, so it's a hybrid architecture.


2014 ◽  
Vol 14 (1) ◽  
pp. 33-61 ◽  
Author(s):  
Alexandru V. Roman

The last two decades have witnessed a tremendous growth in the body of literature addressing the importance and the impact of contracting and public procurement within the context of devolution of government. The austere budgetary and financial outlooks of the future suggest that the significance of the area will only continue to grow. As such, generating explanatory frameworks, within dimensions such as decisionmaking and accountability in public procurement, becomes crucial. Drawing from original research this article suggests one possible frame for understanding administrative decision-making in complex environments. Based on semi-structured interviews with public procurement specialists, the study identifies two decision-making patterns− broker and purist. It is asserted that the decision-making dynamics exhibited by administrators are contingent on their perceptions regarding environmental instability, in particular the political volatility surrounding their work.


Sign in / Sign up

Export Citation Format

Share Document