V-Max: A Reinforcement Learning Framework for Autonomous Driving
This provides a practical tool for researchers in autonomous driving to accelerate RL experimentation, but it is incremental as it builds on existing simulators and methods.
The paper tackles the lack of standardized and efficient research frameworks for reinforcement learning in autonomous driving by introducing V-Max, an open framework built on Waymax and extended with ScenarioNet's approach to enable fast simulation of diverse datasets.
Learning-based decision-making has the potential to enable generalizable Autonomous Driving (AD) policies, reducing the engineering overhead of rule-based approaches. Imitation Learning (IL) remains the dominant paradigm, benefiting from large-scale human demonstration datasets, but it suffers from inherent limitations such as distribution shift and imitation gaps. Reinforcement Learning (RL) presents a promising alternative, yet its adoption in AD remains limited due to the lack of standardized and efficient research frameworks. To this end, we introduce V-Max, an open research framework providing all the necessary tools to make RL practical for AD. V-Max is built on Waymax, a hardware-accelerated AD simulator designed for large-scale experimentation. We extend it using ScenarioNet's approach, enabling the fast simulation of diverse AD datasets.