Visualizing the Evolution of Multi-agent Game-playing Behaviors
Agarwal, Shivam; Latif, Shahid; Rothweiler, Aristide; u. a. (2022): Visualizing the Evolution of Multi-agent Game-playing Behaviors, in: EuroVis 2022 - Posters, Geneve, S. 23–25, doi: 10.2312/EVP.20221111.
Details
- Faculty/Chair
- Faculty/Professorship
- Author
- Agarwal, ShivamLatif, ShahidRothweiler, Aristide
- Title of the compilation
- EuroVis 2022 - Posters
- Corporate Body
- The Eurographics Association
- Conference
- 24th EG Conference on Visualization, 13-17 June 2022, Rome
- Year of publication
- 2022
- ISBN
- 978-3-03868-185-4
- Language
- English
- DOI
- URL
- 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
- MehragentensystemMultivariate DatenSpielverhaltenKünstliche IntelligenzVisualisierung
- Keywords
- Multi-agent systemsmultivariate dataevolving gameplay behaviorsAI trainingvisualization
- DDC Classification
- 004 Computer science
- RVK Classification
- ST 274
- Peer Reviewed
- yes
- International Distribution
- yes
- Open Access Journal
- no
- Type
- Conferenceobject
- URI
- Activation date
- 2022-07-28