{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/74a3b28067e24c1b886054ba90a90aa5\" frameborder=\"0\" width=\"1664\" height=\"1248\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1248,"width":1664,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1248,"thumbnail_width":1664,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/74a3b28067e24c1b886054ba90a90aa5-5442ba3ff082a739.gif","duration":142.2511,"title":"Flight Booking Simulator: Enhancing AI Learning 🌐","description":"In this video, I introduce one of our flight booking simulators where an AI agent is tasked with booking flights from San Francisco to New York for a weekend in September. The simulator mimics real-world environments closely, allowing agents to learn and generalize their skills effectively. We’ve implemented verifiers to check the accuracy of tasks against ground truth data, which serves as a reward signal for reinforcement learning. I'm excited about the growing demand for simulators as we start to integrate multiple environments for multi-application tasks. I encourage you to explore these capabilities and think about how we can leverage them in our projects."}