{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/7dda14bfc31b458eaa472a8d34e352c4\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/7dda14bfc31b458eaa472a8d34e352c4-9b69bf374cc95e7e.gif","duration":78.148,"title":"Enhancing Poker Data Set Environment","description":"In this video, I discuss our efforts to create a robust environment for a new poker data set developed by Yoni, who is an expert in a specific poker format. We have implemented custom reward functions to improve our model's performance, focusing on action matching and bet sizing. I encourage you to subscribe and engage with the content as we refine this environment. Your feedback will be invaluable as we move forward."}