What's better than starting a day full of awesome content in the Machine Learning Summit? Chairs of the summit will introduce the day with a short glance at Machine Learning impact and how it's helping us all creating better games. Each day covers themes that will be explained before heading straight to impactful initiatives!-------------------------------"Streetball Allstar" is a 3v3 street basketball game that attracts players with its real-time competition and fairness. AI bots play an important role in the game. Firstly, they assist beginners in learning and improving, providing examples of exceptional skills and teamwork. Secondly, AI bots serve as teammates or opponents, increasing the diversity and competitiveness of the game. Most importantly, AI bots ensure fair competition, fill the gap when there are not enough players and match players of different tiers with highly customized parameters. In terms of training, we combine reinforcement learning and imitation learning, allowing AI bots to learn a wide range of strategies and simulate human thinking and behavior patterns, possessing human-like qualities and human-AI interaction while also having rich strategy diversity. Through dynamic difficulty control, we can control the operation level of the AI accurately and reasonably, adapting to different skill levels. With the client-side deployment solution, AI bots are decoupled from the core logic of game, improving response speed and ensuring data security. In our demonstration, AI bots have shown outstanding performance in various aspects such as difficulty switching, accurate response, strong adaptability, human-AI interaction, and high stability, receiving enthusiastic praise from both players and our customer.