Advising your Adaptive Software Agent
نویسنده
چکیده
Imagine you are observing the decision-making of a software agent and notice some imperfections. What should you be able to say to it? What would be a good "advice language" that (a) allows one to provide, in a natural, flexible, and imprecise manner, new information to the agent, while (b) ensuring that the agent’s learning mechanism can use the advice? We discuss these questions about broadening the "information pipeline" between human teacher and machine learner, briefly describe an implemented system that provides initial answers, and describe preliminary work on an advice-taking, adaptive Internet wanderer that searches for pages of interest to the user. Our general approach has the following design principles:
منابع مشابه
An Intelligent Natural Language Conversational System for Academic Advising
Academic advisors assist students in academic, professional, social and personal matters. Successful advising increases student retention, improves graduation rates and helps students meet educational goals. This work presents an advising system that assists advisors in multiple tasks using natural language. This system features a conversational agent as the user interface, an academic advising...
متن کاملEvaluation of the Software to Help Advising Professors in Isfahan University of Medical Sciences
Background: One of the essential and inevitable principles in improving the education quality, particularly in universities, is the continuous assessment of students’ educational progress at different education levels. The role of advisors and consulting tutors at universities are considered as one of the important interventions of the Ministry of Health for the purpose of guiding students' st...
متن کاملAdaptive neural control of nonlinear fractional order multi- agent systems in the presence of error constraintion
In this paper, the problem of fractional order multi-agent tracking control problem is considered. External disturbances, uncertainties, error constraints, transient response suitability and desirable response tracking problems are the challenges in this study. Because of these problems and challenges, an adaptive control and neural estimator approaches are used in this study. In the first part...
متن کاملA Learning Environment for Synchronous Tutorial Advising
This paper describes the requirements, the design issues and the implementation of LESTA, an infrastructure supporting Collaborative Distance Learning (CDL) activities for synchronous tutorial advising. Based on client-server architecture, LESTA provides abstraction for modelling users as virtual classes of objects (interfaces) whose interaction is eventbased. Users are, in turn, listeners and ...
متن کاملA multi-agent system for advising and monitoring students navigating instructional Web sites
A growing community of teachers, at all levels of the educational system, provides course material in the form of hypertext/multimedia documents. In most cases this is done by creating a “course Web site”. This paper explores the issues related to the design of software systems that aid teachers in monitoring how students use their sites and proactively advise students navigating the sites. In ...
متن کامل