News

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.

CoreWeave to acquire OpenPipe, a Seattle-area startup that uses reinforcement learning to help companies build AI agents

CoreWeave said it will acquire OpenPipe, a Bellevue, Wash.-based startup that helps developers train AI agents using ...

14B Surpasses 671B! Microsoft's rStar2-Agent Mathematical Reasoning Exceeds DeepSeek-R1, Breakthrough in Agentic Reinforcement Learning

Breakthroughs in Agentic Reinforcement Learning The success of rStar2-Agent can be attributed to three major innovations in ...

TreePO Technology Innovation in AI Training: Making Reinforcement Learning Smarter and More Efficient

Released in August 2025, this research introduces a new method called TreePO (Tree-structured Policy Optimization), aimed at ...
Geeky Gadgets4mon

Why Reinforcement Learning Could Be AI’s Biggest Flaw Yet

Explore the hidden trade-offs of reinforcement learning in AI and why base models might hold the key to true intelligence.
InfoWorld4y

3 ways to get into reinforcement learning | InfoWorld

Whether you like theoretical study or want to get your hands dirty, plenty of reinforcement learning resources are out there.
Nature10y

Human-level control through deep reinforcement learning - Nature

By combining reinforcement learning (selecting actions that maximize reward — in this case the game score) with deep learning (multilayered feature extraction from high-dimensional data — in ...