AI · Video
Training Your Own Agent Models With Reinforcement Learning Is Now Practical, Says Modal's Jason Mancuso
AI Engineer ·
At a glance
Jason Mancuso of Modal presents a video arguing that teams running agents already have what they need to start reinforcement learning (RL, a training method that improves models through rewards). It also argues that treating models as swappable parts has limits.
Key points
- It explains that RL generalizes better than fine-tuning (further training an existing model) on recorded work logs.
- It walks through a stable step-by-step process for asynchronous reinforcement learning using methods such as GRPO.
- It introduces sparse weight updates that spread work across multiple clouds and GPU types.
- The project page says this approach cut rollout (the process of the model actually performing tasks) costs by 15%.
Why it matters
Gives developers and teams that run or improve agents practical approaches to try.
Original source
Training Your Own Agent Models With RL Is Now Practical - Jason Mancuso, Modal
AI Engineer · Nov 9, 17:00 KST
Watch on YouTube ↗AI summarized the video title and description. Check the original for accuracy. Copyright belongs to AI Engineer.
More from this field
- OpenAI Opens ChatGPT Space to Plus Users for Pages, Slides, and Team Sharing
OpenAI opened ChatGPT Space to Plus users on the 20th, local time. Space works as a new home for pages, slides, images, files, and uploads. Users can write pages with ChatGPT, add interactive charts, turn ideas into slides, and invite others to edit together.
AI 매터스 · Nov 21, 11:26 KST - Anthropic Researcher Claims Claude Helped Prove Riemann Hypothesis, Experts Await Review
Wes Roth covers a claim by Anthropic researcher Levent Alpöge that he proved the Riemann Hypothesis with help from the AI model Claude. He looks at the huge Lean formal proof, reactions from mathematicians and AI safety researchers, and what this could mean for AI and math.
Wes Roth · Nov 21, 11:24 KST - Amazon CloudWatch Omni Adds Microsoft Azure Logs, Metrics, and Traces Support
Amazon CloudWatch Omni can now collect Azure resource logs, Azure Monitor platform metrics, virtual network flow logs, and Application Insights traces. Teams running workloads on both AWS and Azure can view all of this telemetry in one place, without separate tools or custom pipelines.
AWS What's New · Nov 21, 10:10 KST - AWS Quick Adds Chat-Built Flows, Updated Web App, and Teamwork Among Agents
AWS Quick added updates that let a team turn one person's work routine into a shared, repeatable process. Flows can now be built and changed entirely in chat, and they can run from the web, desktop, or mobile app. Agents working together can also give more complete answers.
Amazon AWS Machine Learning blog · Nov 21, 10:06 KST