Rinascimento: searching the behaviour space of Splendor
Ivan Bravi, Simon Lucas

TL;DR
This paper introduces Rinascimento, a method using MAP-Elites to explore the behavior space of the game Splendor with AI agents, revealing diverse gameplay behaviors and improving coverage with event-value functions.
Contribution
It presents a novel approach to game play-testing by mapping the behavioral space of Splendor using MAP-Elites, highlighting diverse behaviors and improving exploration with event-value functions.
Findings
Event-value functions enhance behavioral space coverage.
The methodology identifies both exemplary and degenerated behaviors.
AI-based play-testing accelerates game design analysis.
Abstract
The use of Artificial Intelligence (AI) for play-testing is still on the sidelines of main applications of AI in games compared to performance-oriented game-playing. One of the main purposes of play-testing a game is gathering data on the gameplay, highlighting good and bad features of the design of the game, providing useful insight to the game designers for improving the design. Using AI agents has the potential of speeding the process dramatically. The purpose of this research is to map the behavioural space (BSpace) of a game by using a general method. Using the MAP-Elites algorithm we search the hyperparameter space Rinascimento AI agents and map it to the BSpace defined by several behavioural metrics. This methodology was able to highlight both exemplary and degenerated behaviours in the original game design of Splendor and two variations. In particular, the use of event-value…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Games · Sports Analytics and Performance · Reinforcement Learning in Robotics
