Guardado en:
Detalles Bibliográficos
Autores principales: Harmel, Moritz, Paras, Anubhav, Pasternak, Andreas, Roy, Nicholas, Linscott, Gary
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:https://arxiv.org/abs/2312.15122
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929575510933504
author Harmel, Moritz
Paras, Anubhav
Pasternak, Andreas
Roy, Nicholas
Linscott, Gary
author_facet Harmel, Moritz
Paras, Anubhav
Pasternak, Andreas
Roy, Nicholas
Linscott, Gary
contents 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 real-world driving. We bring these capabilities together and conduct large-scale reinforcement learning experiments for autonomous driving. We demonstrate that our policy performance improves with increasing scale. Our best performing policy reduces the failure rate by 64% while improving the rate of driving progress by 25% compared to the policies produced by state-of-the-art machine learning for autonomous driving.
format Preprint
id arxiv_https___arxiv_org_abs_2312_15122
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning
Harmel, Moritz
Paras, Anubhav
Pasternak, Andreas
Roy, Nicholas
Linscott, Gary
Machine Learning
Artificial Intelligence
Robotics
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 real-world driving. We bring these capabilities together and conduct large-scale reinforcement learning experiments for autonomous driving. We demonstrate that our policy performance improves with increasing scale. Our best performing policy reduces the failure rate by 64% while improving the rate of driving progress by 25% compared to the policies produced by state-of-the-art machine learning for autonomous driving.
title Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning
topic Machine Learning
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2312.15122