
Workday's AI Strategy, AI ‘Co-workers’, IPOs Are Back & The Future of Consumer Crypto | Sep 17, 2025
The Information's TITV
00:00
Reinforcement Learning Gyms Explained
Stephanie Palazzolo and Jonathan Siddharth describe why labs build RL gyms: simulated apps, expert labeling, trajectory data, verifiers, and how these environments help agents learn enterprise workflows and tool use.
Transcript
Play full episode