USING LEARNING BY DOING METHODOLOGY FOR TEACHING MULTI-AGENT SYSTEMS
نویسندگان
چکیده
In recent years the teaching of subjects related to Artificial Intelligence has grown notably in higher education degrees. This is case discipline multi-agent systems, which usually part majority master's degrees Intelligence. Multi-agent systems (MAS) offer solutions for distributed decision making, where a set autonomous intelligent agents must reach an agreement solve problem. These types problems are complex and distributed, difficult abstract simplify classroom teaching. The main problem that teachers this subject have face, be able integrate whole techniques algorithms practical example easy understand address within framework planning course.This paper deals with use "learning by doing" methodology Master's Degree at Universitat Politècnica de València. applied avoiding master classes focus on practice. become scientific-technological experience. students teacher team working common purpose, seeking achieve goal. To do this, course been reformulated, proposing different typical MAS area same domain, improvement urban mobility efficient energy cities. It considered sufficiently current topic can motivate student participate propose solutions. objective, system tool developed allows simulate situations proposed develop provides them simulation environment they easily introduce their own strategies carried out each agent. way, challenges negotiation operation taxi fleets, cooperation strategies, help other goal.This tool, called SimFleet, open way published as source, so it used any wishes so, even receive external contributions improvements thanks its character.This learning doing supported SimFleet two consecutive academic obtaining better results assessment than previous courses. Furthermore, satisfaction surveys shown notable increase when using these technologies, reinforces idea type more useful satisfactory students.
منابع مشابه
A Recent Experience in Teaching Multi-Agent Systems Using Jason
This paper briefly describes a recent experience of using Jason for teaching Multi-Agent Systems. Jason is a Java-based interpreter for an extended version of AgentSpeak. The basic AgentSpeak programming language for BDI agents is rather simple, making Jason a suitable tool for students to put into practice some of the elements of the BDI theory covered in the lectures.
متن کاملVariable Structure Behavioural Controller for Multi-agent Systems
In previous papers authors have considered agents as inertia-less self driven particles and designed a flocking algorithm. Application of this algorithm to agents with considerable inertial characteristics needs a behavioural controller. The controller uses the local information and helps every agent to imitate the desired behaviour as a member of the flocking frame which covers the main is...
متن کاملMASD: Multi-agent systems development methodology
In recent years, multi-agent systems gained growing acceptance as a required technology to develop complex distributed systems. As result, there is an increased need for practical methodology for developing such systems. This paper presents a new Multi-Agent System Development (MASD) methodology developed over several years through analyzing and studying most of the existing agent oriented meth...
متن کاملOptimization of majority protocol for controlling transactions concurrency in distributed databases by multi-agent systems
In this paper, we propose a new concurrency control algorithm based on multi-agent systems which is an extension of majority protocol. Then, we suggest a clustering approach to get better results in reliability, decreasing message passing and algorithm’s runtime. Here, we consider n different transactions working on non-conflict data items. Considering execution efficiency of some different...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: INTED proceedings
سال: 2021
ISSN: ['2340-1087', '2340-1079']
DOI: https://doi.org/10.21125/inted.2021.0794