# Using Reinforcement Learning for Load Testing of Video Games

arXiv: https://arxiv.org/abs/2201.06865 · HTML: https://mlsanity.com/paper/2201.06865/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2022.

## Built on by (most cited first, 11 of 11)

- [A Comparison of Reinforcement Learning Frameworks for Software Testing Tasks](https://mlsanity.com/paper/2208.12136/) (2022)
- [Preference-conditioned Pixel-based AI Agent For Game Testing](https://mlsanity.com/paper/2308.09289/) (2023)
- [Monte Carlo Beam Search for Actor-Critic Reinforcement Learning in Continuous Control](https://mlsanity.com/paper/2505.09029/) (2025)
- [Bayesian Optimization-based Search for Agent Control in Automated Game Testing](https://mlsanity.com/paper/2508.13121/) (2025)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [On Automating Video Game Regression Testing by Planning and Learning](https://mlsanity.com/paper/2402.12393/) (2024)
- [Leveraging Reward Models for Guiding Code Review Comment Generation](https://mlsanity.com/paper/2506.04464/) (2025)
- [Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning](https://mlsanity.com/paper/2509.11880/) (2025)
- [Towards Reinforcement Learning Based Log Loading Automation](https://mlsanity.com/paper/2510.26363/) (2025)
- [Play Like Champions: Counterfactual Feedback Generation in Latent Space](https://mlsanity.com/paper/2607.00190/) (2026)
- [Evaluating VLMs for Autonomous Agent-Driven Geometry Clipping Detection in Video Game QA](https://mlsanity.com/paper/2607.25921/) (2026)

## Abstract (arXiv)

Different from what happens for most types of software systems, testing video games has largely remained a manual activity performed by human testers. This is mostly due to the continuous and intelligent user interaction video games require. Recently, reinforcement learning (RL) has been exploited to partially automate functional testing. RL enables training smart agents that can even achieve super-human performance in playing games, thus being suitable to explore them looking for bugs. We investigate the possibility of using RL for load testing video games. Indeed, the goal of game testing is not only to identify functional bugs, but also to examine the game's performance, such as its ability to avoid lags and keep a minimum number of frames per second (FPS) when high-demanding 3D scenes are shown on screen. We define a methodology employing RL to train an agent able to play the game as a human while also trying to identify areas of the game resulting in a drop of FPS. We demonstrate the feasibility of our approach on three games. Two of them are used as proof-of-concept, by injecting artificial performance bugs. The third one is an open-source 3D game that we load test using the trained agent showing its potential to identify areas of the game resulting in lower FPS.