Automatic Bug Detection in Games using LSTM Networks
arXiv:2312.08418v15 citationsh-index: 92023 IEEE Conference on Games (CoG)
Originality Synthesis-oriented
AI Analysis
This addresses bug detection for game developers, but it appears incremental as it applies an existing method (LSTM) to a new domain (games).
The authors tackled the problem of detecting perceptual bugs in video games by introducing a framework using LSTM networks to identify anomalies and cluster buggy frames, showing effectiveness in evaluations on two FPS games.
We introduced a new framework to detect perceptual bugs using a Long Short-Term Memory (LSTM) network, which detects bugs in video games as anomalies. The detected buggy frames are then clustered to determine the category of the occurred bug. The framework was evaluated on two First Person Shooter (FPS) games. Results show the effectiveness of the framework.