News

SJTU and ByteDance Join Forces to Launch RhymeRL: 2.6x Improvement in Reinforcement Learning Training Speed!

This similarity primarily arises from mainstream RL algorithms such as PPO/GRPO, which use gradient clipping mechanisms to ensure training stability. This mechanism smooths the model's evolutionary ...

Conquering the 'Slowest Link' in Reinforcement Learning! Joint Efforts of Shanghai Jiao Tong University and ByteDance Boost RL Training Speed by 2.6 Times

However, behind this competition, a huge bottleneck quietly limits the speed of all players—compared to pre-training and ...
EurekAlert!

Reinforcement learning is making a buzz in space

A U.S. Naval Research Laboratory (NRL) research team successfully conducted the first reinforcement learning (RL) control of ...
VentureBeat

OpenAI launches reinforcement learning training to prepare for artificial general intelligence

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More OpenAI today announced the launch of Spinning Up, a program designed to ...

CoreWeave to Acquire OpenPipe, Leader in Reinforcement Learning

CoreWeave, Inc. (NASDAQ: CRWV), the AI Hyperscaler™, today announced a definitive agreement to acquire OpenPipe Inc, a ...

CoreWeave acquires agent-training startup OpenPipe

CoreWeave hopes the YC-backed startup will help it expand up the stack and cash in on enterprises developing AI agents.

Astrus Secures $8M USD to Accelerate AI-Driven Microchip Design

New funding will help Astrus expand its team and deliver AI tools that accelerate chip development for leading semiconductor ...
usace.army.mil

Army research leads to more effective training model for robots

ADELPHI, Md.-- Multi-domain operations, the Army’s future operating concept, requires autonomous agents with learning components to operate alongside the warfighter. New Army research reduces the ...