The post-training revolution: How reinforcement learning is upending the AI infra stack

TechCrunch was proud to host Scale Venture Partners at Disrupt 2025 in San Francisco. Here’s an overview of their AI Stage session.  The reinforcement learning market has exploded, with enterprises ...
The Robot Report

AgiBot deploys its Real-World Reinforcement Learning system

AgiBot said its Real-World Reinforcement Learning system lets robots learn new skills in minutes on a pilot production line.
Deep Learning with Yacine on MSN

Group Relative Policy Optimization (GRPO) Explained – Formula and PyTorch Implementation

Discover how Group Relative Policy Optimization (GRPO) works with a clear breakdown of the core formula and working Python ...

AgiBot Makes History: First Robot to Learn Directly on the Factory Floor

AgiBot builds world’s first real-world deployment of reinforcement learning in industrial robotics, bringing self-learning AI to manufacturing ...
MyHorryNews

AgiBot Achieves First Real-World Deployment of Reinforcement Learning in Industrial Robotics

SHANGHAI, Nov. 2, 2025 /PRNewswire/ -- AgiBot, a robotics company specializing in embodied intelligence, announced a key milestone with the successful deployment of its Real-World Reinforcement ...
IEEE

Warfarin Dose Management Using Offline Deep Reinforcement Learning

Abstract: Warfarin is a commonly prescribed anticoagulant with a narrow therapeutic window, which requires frequent and specialized monitoring. This work aims to develop standardized optimal warfarin ...
IEEE

Reinforcement Learning Solutions for Microgrid Control and Management: A Survey

Abstract: A microgrid (MG) is part of a distribution system that comprises loads and distributed energy resources, capable of operating either connected to or islanded from the primary grid. Having an ...
GitHub

Overview - Universal Multi-Language Runner

run is a universal multi-language runner and smart REPL (Read-Eval-Print Loop) written in Rust. It provides a unified interface for executing code across 25 programming languages without the hassle of ...

Thinking Machines challenges OpenAI's AI scaling strategy: 'First superintelligence will be a superhuman learner'

Thinking Machines Lab challenges OpenAI’s scaling-first approach to artificial intelligence, arguing that true ...

Inside Ring-1T: Ant engineers solve reinforcement learning bottlenecks at trillion scale

Ant Group, an affiliate of Alibaba, released Ring-1T which it says is the first trillion parameter open-source model.
marktechpost

RA3: Mid-Training with Temporal Action Abstractions for Faster Reinforcement Learning (RL) Post-Training in Code LLMs

TL;DR: A new research from Apple, formalizes what “mid-training” should do before reinforcement learning RL post-training and introduces RA3 (Reasoning as Action Abstractions)—an EM-style procedure ...