SEED Research & Announcements Blogs Publications Open Source Careers Contact Us Research & Announcements Blogs Publications Open Source Careers Contact Us

CoG 21: Improving Playtesting Coverage via Curiosity Driven Reinforcement Learning Agents

This research paper has been accepted for publication at IEEE Conference on Games 2021.

As modern games continue growing both in size and complexity, it has become more challenging to ensure that all the relevant content is tested and that any potential issue is properly identified and fixed. Attempting to maximize testing coverage using only human participants, however, results in a tedious and hard to orchestrate process which normally slows down the development cycle.

Complementing playtesting via autonomous agents has shown great promise in accelerating and simplifying this process.

This paper addresses the problem of automatically exploring and testing a given scenario using reinforcement learning agents trained to maximize game state coverage. Each of these agents is rewarded based on the novelty of its actions, thus encouraging a curious and exploratory behaviour in a complex 3D scenario where previously proposed exploration techniques perform poorly. The curious agents are able to learn the complex navigation mechanics required to reach the different areas around the map, thus providing the necessary data to identify potential issues.

Moreover, the paper also explores different visualization strategies and evaluates how to make better use of the collected data to drive design decisions and to recognize possible problems and oversights.

Download the research paper: https://arxiv.org/abs/2103.13798

test

Related News

Gigi Lightning Talks

SEED
Sep 26, 2024
SEED brought together developers to show off their prowess using the Gigi rapid prototyping platform for real-time rendering.

SEED's Adventure in Gameplay Innovation

SEED
Sep 13, 2024
SEED is branching out into the world of game mechanics, storytelling magic, and interactive wonders.

Objective Metrics for Evalutating Gesture Generation are Almost Useless

SEED
Sep 10, 2024
How do you evaluate something as subjective and ephemeral as human body language for natural and lifelike qualities?