Building Custom Models That Know Your Enterprise Knowledge with Reinforcement Learning

In this session, we will discuss how Databricks is using reinforcement learning to customize open source models to power our internal agents at a fraction of the cost and much higher speed. We will also discuss how our customers are using the same tools on Databricks AI Runtime (AIR) to do the same thing for their enterprise agents. We will go over the ingredients needed to successfully perform custom RL, the process of developing custom models using RL, and the novel tools and RL methods we have developed at Databricks to make this powerful technology available for enterprises.