mlsanityData to 7 Oct 2026

A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7

arXiv 2504.09021 ↗First posted 12 Apr 2025cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning has achieved superhuman racing performance in high-fidelity simulators like Gran Turismo 7 (GT7). It typically utilizes global features that require instrumentation external to a car, such as precise localization of agents and opponents, limiting real-world applicability. To address this limitation, we introduce a vision-based autonomous racing agent that relies solely on ego-centric camera views and onboard sensor data, eliminating the need for precise localization during inference. This agent employs an asymmetric actor-critic framework: the actor uses a recurrent neural network with the sensor data local to the car to retain track layouts and opponent positions, while the critic accesses the global features during training. Evaluated in GT7, our agent consistently outperforms GT7's built-drivers. To our knowledge, this work presents the first vision-based autonomous racing agent to demonstrate champion-level performance in competitive racing scenarios.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 12 Apr 2025.

Builds on

28 of 46 references.

References · 28

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  5. 2020Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixelscited by 573
  6. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 464
  7. 2020Reinforcement Learning with Augmented Datacited by 452
  8. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  9. 2019Improving Sample Efficiency in Model-Free Reinforcement Learning from Imagescited by 268
  10. 2022The Primacy Bias in Deep Reinforcement Learningcited by 242
  11. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 202
  12. 2020Super-Human Performance in Gran Turismo Sport Using Deep Reinforcement Learningcited by 60
16 more
  1. 2022Autonomous Vehicles on the Edge: A Survey on Autonomous Vehicle Racingcited by 56
  2. 2023PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learningcited by 42
  3. 2021Autonomous Overtaking in Gran Turismo Sport Using Curriculum Reinforcement Learningcited by 41
  4. 2018End-to-End Race Driving with Deep Reinforcement Learningcited by 38
  5. 2021Learn-to-Race: A Multimodal Control Environment for Autonomous Racingcited by 23
  6. 2021Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learningcited by 21
  7. 2019Controlling an Autonomous Vehicle with Deep Reinforcement Learningcited by 12
  8. 2024A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismocited by 12
  9. 2020Optimization-Based Hierarchical Motion Planning for Autonomous Racingcited by 11
  10. 2021Formula RL: Deep Reinforcement Learning for Autonomous Racing using Telemetry Datacited by 10
  11. 2024AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobilitycited by 10
  12. 2022Motion Planning and Control for Multi Vehicle Autonomous Racing at High Speedscited by 8
  13. 2020Minimum Race-Time Planning-Strategy for an Autonomous Electric Racecarcited by 4
  14. 2023Adaptive Planning and Control with Time-Varying Tire Models for Autonomous Racing Using Extreme Learning Machinecited by 4
  15. 2023Learning Model Predictive Control with Error Dynamics Regression for Autonomous Racingcited by 4
  16. 2024A Simulation Benchmark for Autonomous Racing with Large-Scale Human Datacited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Automated Reward Design for Gran Turismocited by 2
  2. 2025Agile Flight Emerges from Multi-Agent Competitive Racingcited by 2
  3. 2025Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Drivingcited by 0
  4. 2026Self-Paced Curriculum Reinforcement Learning for Autonomous Superbike Racing in Simulationcited by 0