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 ...

Policy (Consumer): Replicas of training instances Rollout (Producer): Replicas of generation engines Low-precision training (FP8) and rollout (FP8 & FP4) support This project will download and install ...

Abstract: Motivated by modern applications such as computerized adaptive testing, sequential rank aggregation, and heterogeneous data source selection, we study the problem of active sequential ...

Greed isn’t always as obvious as someone hoarding stacks of gold like a modern-day dragon. Sometimes, it’s subtle, wrapped in polished manners, or cleverly disguised as ambition. The signs of greed ...