Training Agents with Reinforcement Learning

Hosted by Will Brown

Thu, Jun 12, 2025

10:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

483 students

Invite your network

Go deeper with a course

Production-Ready Agent Engineering: From MCP to RL
Will Brown and Kyle Corbitt
View syllabus

What you'll learn

A crash course in RL for LLMs

Overview of RL basics: policies, actions, environments, rewards, how it relates to LLMs via GRPO

How to build "RL-ready" agents

Walkthrough of building a search agent + how to prototype environments via tool integrations + offline evaluations

Tips and tricks for RL training

Recipes for improving your agent via online RL training with GRPO

Why this topic matters

2025 is the Year of the Agents, everyone's talking about RL, but it might seem complicated and inaccessible. It doesn't have to be. RL gives you a set of tools for actually improving your agent models to be performant and cost-effective without relying on closed-source API models.

You'll learn from

Will Brown

Research Lead at Prime Intellect

Will is a Research Lead at Prime Intellect, working on advancing the frontier of open-source agentic RL. He was previously a Machine Learning Researcher at Morgan Stanley and an Applied Scientist at AWS, and completed a PhD in Computer Science at Columbia University focused on multi-agent learning.

Learn directly from Will Brown

By continuing, you agree to Maven's Terms and Privacy Policy.

© 2025 Maven Learning, Inc.