Home > Research > Publications & Outputs > Bang: a system for training and visualization i...

Research

Associated organisational units

Electronic data

Links

View graph of relations

Bang: a system for training and visualization in multi-agent team formation

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published
Close
More...
Publication date8/05/2017
Host publicationAAMAS '17 Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems São Paulo, Brazil — May 08 - 12, 2017
Place of PublicationRichland, SC
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems
Pages1781-1783
Number of pages3
<mark>Original language</mark>English

Abstract

In this demo participants will explore Bang, a system for multiagent team formation. Bang automatically selects exercises for training agents, and allows an operator to visualize the expected
performance of possible teams, guiding in the agent selection process.
Bang is used in the context of programming competitions, a real-world challenge that involves human teams, and significantly improved the performance of the teams of CEFET-MG University.