video1.0<iframe src="https://www.loom.com/embed/f2cd3eb1de894526b878b88f4e43eeba" frameborder="0" width="1662" height="1246" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12461662Loomhttps://www.loom.com12461662https://cdn.loom.com/sessions/thumbnails/f2cd3eb1de894526b878b88f4e43eeba-800868a7dccdd066.gif109.902In this video, I demonstrate how to create a reinforcement learning environment using our AI studio and the CodeX SDK. I set up a vacuum cleaner agent that navigates obstacles to collect dirt and return to its original space, showcasing the actions, observation space, and rewards generated. We can train the agent for up to 15,000 steps, and I noticed that while the rewards increased, we might need to adjust the training parameters for better results. I encourage you to explore creating your own environments and experimenting with the training process. Please let me know if you have any questions or need assistance!