Bot Name: KillAll Bot Race: Zerg Author Name(s): Zhentao Tang Affiliation(s): University of Chinese Academy of Science Nationality(s): China Occupation(s): Student (These will be listed on the competition website) Bot URL: None Personal URL:None Affiliation URL: http://www.gucas.ac.cn/ Questions about your bot (please answer as many as you can, especially Q 1-3) Q: What is the overall strategy/strategies of your bot? Why did you choose them? The bot has different strategies towards differnet enemy races. It took defence and fighting back strategy for the Zerg with help of Multalisks and Zerglings. And it took advantage of the early zergling rush to Terran and Protoss. In addition, it also has some different opening strategies: Five-Poolings, Nine-Poolings, TwoHatchMuta and so on. Q: Do you incorporate learning of any form in your bot? If so, how was it accomplished? Currently, it has not got here. Q: Please describe all AI techniques / algorithms used in your bot. (For example: What parts of your bot are 'hard-coded', which use learning, search, decision trees, state machines, etc) Most of this Bot is "hard-code", but the production module is depended on Q-Learning Method for select the most suitable choices of production of Zerg Battle Army (Zerglings, Hydralisks, Mutalisks) and it's based on the Overkill from Sijia Xu. Q: How did you become interested in Starcraft AI? When I was young, I liked playing computer games, such as Need for Speed, CS, StarCraft. And now I has the chance to create a bot for AI game, it is really makes me so excited. Q: How long have you been working on your bot? It's about 2 months. Q: About how many lines of code is your bot? I can't remerber, maybe it 20 thousand or 30 thousand lines. Q: Why did you choose the race of your bot? Because I like Sijia Xu's Overkill, then I choose Zerg. Q: Did you use any existing code as the basis for your bot? If so, why, and what did you change? I have used Overkill's production module and SparCraft's Micro manager module. But I have also improve the strategy more rational towards differenct enemy races. Q: What do you feel are the strongest and weakest parts of your bot's overall performance? There is not strongest or weakest parts, but I think it is really a balance for all modules. Q: If you competed in previous tournaments, what did you change for this year's entry? No, it's my first time. Q: Have you tested your bot against humans? If so, how did it go? Yes, it is totally defeat me. But I am not good at playing StarCraft. Q: Any fun or interesting stories about the development / testing of your bot? Yes, But I could not remember now.:) Q: Any other projects you're working on that you'd like to advertise? Not now. Optional Opinion Questions: Q: What is your opinion on the current state of StarCraft AI? How long do you think before computers can beat humans in a best-of-7 match? See deepMind made it happened. Q: What do you feel is the biggest hurdle (technological or otherwise) in improving your bot's AI? Strategy. I think hard-code should not be the best approach to solve the StarCraft Game Problem. But right now I have not idea on it. Q: Which bots are the most interesting to you and why? Facebook's. Hope they have some creative ideas on StarCraft AI.