An engineering thesis disguised as a coupe: A history of the Honda Prelude

The Honda Prelude was never simply a car. It was an engineering thesis disguised as a coupe: compact, disciplined, and unapologetically technical. At its best, it distilled Hondas ...
Top Speed

The Japanese Six-Cylinder Engine That Refused To Be Replaced

Over the past 70 years, Japanese brands have refined a unique approach that combines rigorous quality control with the use of ...
GitHub

PRIME-RL: Async RL Training at Scale

PRIME-RL is a framework for large-scale asynchronous reinforcement learning. It is designed to be easy-to-use and hackable, yet capable of scaling to 1000+ GPUs. Beyond that, here is why we think you ...
GitHub

Zero Shot Reinforcement Learning from Low Quality Data

Figure 1: Conservative zero-shot RL methods suppress the values or measures on actions not in the dataset for all tasks. Black dots represent state-action samples present in the dataset. This work ...