
From Prompts to Policies: How RL Builds Better AI Agents with Mahesh Sathiamoorthy - #731
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Intro
This chapter explores the disconnect between successful AI demonstrations and the difficulties encountered in real-world applications. It also introduces a live course aimed at training listeners on evaluation workflows, including the importance of reinforcement learning and advanced fine-tuning techniques.
Transcript
Play full episode