Augmenting Automated Game Testing with Deep Reinforcement Learning
This addresses the need for more efficient and automated testing in the gaming industry, though it appears incremental as it applies existing DRL methods to a new domain.
The paper tackled the problem of automating game testing by introducing a deep reinforcement learning (DRL) framework that explores and exploits game mechanics based on reward signals, resulting in increased test coverage and discovery of bugs and exploits across various game types, including first-person shooter games.
General game testing relies on the use of human play testers, play test scripting, and prior knowledge of areas of interest to produce relevant test data. Using deep reinforcement learning (DRL), we introduce a self-learning mechanism to the game testing framework. With DRL, the framework is capable of exploring and/or exploiting the game mechanics based on a user-defined, reinforcing reward signal. As a result, test coverage is increased and unintended game play mechanics, exploits and bugs are discovered in a multitude of game types. In this paper, we show that DRL can be used to increase test coverage, find exploits, test map difficulty, and to detect common problems that arise in the testing of first-person shooter (FPS) games.