# Expert Human-Level Driving in Gran Turismo Sport Using Deep Reinforcement Learning with Image-based Representation

arXiv: https://arxiv.org/abs/2111.06449 · HTML: https://mlsanity.com/paper/2111.06449/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 11 Nov 2021.

## Builds on (most cited first, 17 of 17)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Decoupling Representation Learning from Reinforcement Learning](https://mlsanity.com/paper/2009.08319/) (2020)
- [PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settings](https://mlsanity.com/paper/1905.01296/) (2019)
- [Multiple Futures Prediction](https://mlsanity.com/paper/1911.00997/) (2019)
- [CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving](https://mlsanity.com/paper/1807.03776/) (2018)
- [Playing FPS Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05521/) (2016)
- [Driving Policy Transfer via Modularity and Abstraction](https://mlsanity.com/paper/1804.09364/) (2018)
- [Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learning](https://mlsanity.com/paper/2008.07971/) (2020)
- [Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learning](https://mlsanity.com/paper/2103.14666/) (2021)
- [End-to-End Race Driving with Deep Reinforcement Learning](https://mlsanity.com/paper/1807.02371/) (2018)
- [High-speed Autonomous Drifting with Deep Reinforcement Learning](https://mlsanity.com/paper/2001.01377/) (2020)
- [Deep Learning and Control Algorithms of Direct Perception for Autonomous Driving](https://mlsanity.com/paper/1910.12031/) (2019)

## Built on by (most cited first, 3 of 3)

- [A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo](https://mlsanity.com/paper/2406.12563/) (2024)
- [A Comprehensive Review of Multi-Agent Reinforcement Learning in Video Games](https://mlsanity.com/paper/2509.03682/) (2025)
- [Parallel Neural Computing for Scene Understanding from LiDAR Perception in Autonomous Racing](https://mlsanity.com/paper/2412.18165/) (2024)

## Abstract (arXiv)

When humans play virtual racing games, they use visual environmental information on the game screen to understand the rules within the environments. In contrast, a state-of-the-art realistic racing game AI agent that outperforms human players does not use image-based environmental information but the compact and precise measurements provided by the environment. In this paper, a vision-based control algorithm is proposed and compared with human player performances under the same conditions in realistic racing scenarios using Gran Turismo Sport (GTS), which is known as a high-fidelity realistic racing simulator. In the proposed method, the environmental information that constitutes part of the observations in conventional state-of-the-art methods is replaced with feature representations extracted from game screen images. We demonstrate that the proposed method performs expert human-level vehicle control under high-speed driving scenarios even with game screen images as high-dimensional inputs. Additionally, it outperforms the built-in AI in GTS in a time trial task, and its score places it among the top 10% approximately 28,000 human players.