Authors
- Hojoon Lee
- Takuma Seno
- Jun Jet Tai
- Kaushik Subramanian
- Kenta Kawamoto
- Peter Stone
- Peter R. Wurman
Venue
- RA-L
Date
- 2025
A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7
Hojoon Lee
Takuma Seno
Jun Jet Tai
Peter R. Wurman
RA-L
2025
Abstract
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.
Related Publications
Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment. Referred to as ``zero-shot learning," this ability remains elusive for general-purpose reinforcement learning algorithms. While rec…
Scaling up the model size and computation has brought consistent performance improvements in supervised learning. However, this lesson often fails to apply to reinforcement learning (RL) because training the model on non-stationary data easily leads to overfitting and unstab…
While existing vision and multi-modal foundation models can handle multiple computer vision tasks, they often suffer from significant limitations, including huge demand for data and computational resources during training and inconsistent performance across vision tasks at d…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.