Feel free to answer as many questions as you like, but it would be great if everyone answered everything! Please feel free to provide external references/links as necessary Bot Name: BTHAI Bot Race: Terran in the tournament, but can play all races. Author Name(s): Johan Hagelbäck Affiliation(s): Linnaeus University Nationality(s): Sweden Occupation(s): Assistant Professor Q: How did you become interested in Starcraft AI? I have worked with RTS games since the beginning of my Ph.D. studies in 2007. I took part in the early ORTS tournaments before BWAPI was developed. Q: How long have you been working on your bot? It took about a year to develop the foundation. Then it has mostly been tweaks and bugfixes. Q: About how many lines of code is your bot? No idea. I should check som day :) Q: Why did you choose the race of your bot? The first year I actually played as Zerg, but the bot in its current state is strongest playing as Terrans. Q: Did you use any existing code as the basis for your bot? If so, why, and what did you change? Developed everything from scratch. Q: What is the overall strategy/strategies of your bot? Why did you choose them? Start with a strong defence to fend of early rushes. The bot constructs quite large, well-balanced squads with mixed units and tries to win by using clever tactical navigation and surround the enemy. Q: Do you incorporate learning of any form in your bot? If so, how was it accomplished? There is a learning module that was not used in the tournament. It uses a pool of static tactics and keeps track of win rates for each of the tactics, and has the highest probability of selecting a successful tactic. Q: Do you use any interesting AI techniques or algorithms in your bot? If so, which? The tactical navigation can use both Potential Fields and Flocking algorithms. Both are almost equally effective, but the Potential Fields version requires much more CPU time. Q: What do you feel are the strongest and weakest parts of your bot's overall performance? It is week against drops and flying attacks to the base. The tactic is also very static and I think the bot would be much better with some kind of dynamic tactics. I have ideas so if I am lucky I have time to implement it to next year's tournament. Q: If you competed in previous tournaments, what did you change for this year's entry? BTHAI finished last two years in a row and this year it was quite successful, ending in the middle even with around 25% crash rate. The main things that was changed was critical bugfixes. Last two years units could stand idle without attacking enemy units even if within fire range. Also the Potential Fields navigation system was exchanged to a Flocking-based system. Q: Have you tested your bot against humans? If so, how did it go? Only with a very early version. It won against novices, but had a hard time against experienced players. Q: Any fun or interesting stories about the development / testing of your bot? Not really. Just many hours of frustrating bug fixes :) Q: Any other projects you're working on that you'd like to advertise? I recently changed affiliation and is mainly focus on research in robotics. I have to work on the bot in my spare time. 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? In 5 years of time I think it is do-able, excent against Koreans ;) Q: What do you feel is the biggest hurdle (technological or otherwise) in improving your bot's AI? Time. Q: Which bots are the most interesting to you and why? AIUR. I think the learning part is very interesting!