Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning

Reinforcement learning has been demonstrated to outperform even the best humans in complex domains like video games. However, running reinforcement learning experiments on the required scale for autonomous driving is extremely difficult. Building a large scale reinforcement learning system and distributing it across many GPUs is challenging. Gathering experience during training on real world vehicles is prohibitive from a safety and scalability perspective. Therefore, an efficient and realistic driving simulator is required that uses a large amount of data from …

autonomous autonomous driving building cs.ai cs.lg cs.ro domains driving experience games gpus humans jax reinforcement reinforcement learning running scale scaling video video games