Cloudflare Introduces Clef Open-Source Decision Models and RL Fine-Tuning Platform
Cloudflare has introduced Clef, open-source decision models and an RL fine-tuning platform, signaling a push toward trainable AI control systems for builders.
Reinforcement Learning
Latest News and Analysis in Reinforcement Learning
Reinforcement Learning
NVIDIA Details Agent-Driven Workflow for Cross-Embodiment Robot Navigation
NVIDIA’s COMPASS tutorial shows how AI agents can automate simulation, residual reinforcement learning, and evaluation for robot navigation across platforms.
NVIDIA pushes agent reinforcement learning into the enterprise playbook with Nemotron 3 Super and NeMo RL guidance
NVIDIA says RLVR and GRPO are now practical for enterprise AI agents, tying Nemotron 3 Super and NeMo RL to domain-specific reliability gains.
General Intuition Raises $320M on $2.3B Bet That Video Games Can Train Real-World AI Agents
General Intuition has raised $320 million to scale AI trained on millions of hours of gameplay, betting action data can help AI develop real-world reasoning.
DeepMind Veteran David Silver Raises $1 Billion Seed Round to Build Superintelligence Without LLMs
Former Google DeepMind researcher David Silver is raising a record $1 billion seed round led by Sequoia Capital for his London-based startup Ineffable Intelligence, which aims to build superintelligence using reinforcement learning rather than large language models.
Ads