Visualizing the Evolution of Multi-agent Game-playing Behaviors
Faculty/Professorship: | Information Visualisation |
Author(s): | Agarwal, Shivam ![]() ![]() ![]() |
Title of the compilation: | EuroVis 2022 - Posters |
Corporate Body: | The Eurographics Association |
Conference: | 24th EG Conference on Visualization, 13-17 June 2022, Rome |
Publisher Information: | Geneve |
Year of publication: | 2022 |
Pages: | 23-25 |
ISBN: | 978-3-03868-185-4 |
Language(s): | English |
DOI: | 10.2312/EVP.20221111 |
URL: | https://diglib.eg.org/bitstream/handle/10.2312/... |
Abstract: | Analyzing the training evolution of AI agents in a multi-agent environment helps to understand changes in learned behaviors, as well as the sequence in which they are learned. We train an existing Pommerman team from scratch and, at regular intervals, let it battle against another top-performing team. We define thirteen game-specific behaviors and compute their occurrences in 600 matches. To investigate the evolution of these behaviors, we propose a visualization approach and showcase its usefulness in an application example. |
GND Keywords: | Mehragentensystem; Multivariate Daten; Spielverhalten; Künstliche Intelligenz; Visualisierung |
Keywords: | Multi-agent systems, multivariate data, evolving gameplay behaviors, AI training, visualization |
DDC Classification: | 004 Computer science |
RVK Classification: | ST 274 |
Peer Reviewed: | Ja |
International Distribution: | Ja |
Type: | Conferenceobject |
URI: | https://fis.uni-bamberg.de/handle/uniba/54954 |
Release Date: | 28. July 2022 |

originated at the
University of Bamberg
University of Bamberg