[2312.15122] Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack
[2312.15122] Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2312.15122 (cs) [Submitted on 23 Dec 2023 ( v1 ), last revised 5 Nov 2024 (this version, v4)] Title: Scaling Is All You Need: Autonomous Driving with JAX-Accelerated Reinforcement Learning Authors: Moritz Harmel , Anubhav Paras , Andreas Pasternak , Nicholas Roy , Gary Linscott View a PDF of the paper titled Scal
related reading
- Q-learning is not yet scalableseohong.me
- Just Ask for Generalization | Eric Jangevjang.com
- The upcoming GPT-3 moment for RL | Mechanize, Inc.mechanize.work
- Human-compatible driving partners through data-regularized self-play reinforcement learningarxiv.org
- Building reliable sim driving agents by scaling self-playarxiv.org
- Using JAX to accelerate our research — Google DeepMinddeepmind.com
- Selected Publicationsjoschu.net
- It Looks Like You’re Trying To Take Over The World · Gwern.net (reader mode)gwern.net
- [2412.14135] Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspectivearxiv.org
- [2103.06326] S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningarxiv.org
- Learning Sim-to-Real Humanoid Locomotion in 15 Minutesyounggyo.me
- [2606.05555] Representation Learning Enables Scalable Multitask Deep Reinforcement Learningarxiv.org