AIIDE StarCraft AI Competition - Survey

Feel free to answer as many questions as you like, but it would be great if everyone answered everything!
Many people are interested in learning as much as possible about the bots that competed!
Please feel free to provide external references/links as necessary

Bot Name:			CSE
Bot Race:			Protoss
Author Name(s):		Junge Zhang, Wei Guo, Qiyue Yin, Dong Zhan, Qiwei Wang, Yihui Hu, Shengqi Shen, Kaiqi Huang
Affiliation(s):		No
Nationality(s):		PR China
Occupation(s):		No

(These will be listed on the competition website)
Bot URL:			No
Personal URL:		No
Affiliation URL:	No

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?
   >> Our bot is mainly based on 'hard-coded' rules plus some machine learning methods. The 'hard-coded' rules are more effective, while the learning methods can be a supplement.
Q: Did you incorporate any of the following AI techniques in your bot?
   If you did, please be as specific as possible
   >> We use a multilayer perception network and several rules to predict units to train when the build order queue is empty. Also, Our bot is based on Locutus, it has all the AI ​​technologies that come with Locutus.

Q: How did you become interested in Starcraft AI?
	>> It is a good testbed for Artificial General Intelligence.

Q: How long have you been working on your bot?
	>> Six weeks.
	
Q: About how many lines of code is your bot?
	>> Our bot is based on Locutus, plenty of changes have been made. It's 53634 lines of code in all the header and source files.

Q: Why did you choose the race of your bot?
	>> We watched a lot of PvT and PvP replays, and decided to make a Locutus-based Protoss bot.

Q: Did you use any existing code as the basis for your bot? If so, why, and what did you change?
	>> Our bot is based on Locutus, which is an excellent bot. The general framework is not changed, i.e., relation among different modules. We made several changes in strategy and micro:
		- Our bot runs the same basic build order every time in PvP match (except on the map "Heart Break Ridge"), it modifies the build order and micro by scouting enemy's strategy and previous match records. 
		- We also tried to use proxy rush on the map "Heart Break Ridge" in PvP match. Because we found that it's hard to defend proxy rush on that specific map. 
		- We use a multilayer perception network and several rules to predict units to train when the build order queue is empty.

Q: What do you feel are the strongest and weakest parts of your bot's overall performance?
	>> Strongest parts: PvP match.
	>> Weakest parts: PvT match, since we don't have much time to improve PvT strategies.
	
Q: If you competed in previous tournaments, what did you change for this year's entry?
	>> We competed with bot cpac last year, but CSE is very different from cpac. They use different race and based-on different bots.

Q: Have you tested your bot against humans? If so, how did it go?
	>> Our bot can beat amateur player sometimes, but it will be defeated once the rules are learned by the human. 

Q: Any fun or interesting stories about the development / testing of your bot?
	>> We built several "imaginary enemy bots" to test our bot. Each of them uses different strategy to counter CSE. Finally, CSE can detect all these strategies by scouting and defeat these "enemies".

Q: Any other projects you're working on that you'd like to advertise?
	>> None.


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?
	>> It will take a long time to design bots that can beat top human players.

Q: What do you feel is the biggest hurdle (technological or otherwise) in improving your bot's AI?
	>> Our time for developing CSE is very limited, we still want to implement a lot of features, but don't have enough time to do so.

Q: Which bots are the most interesting to you and why?
	>> SAIDA and Cherry Pi. SAIDA is an excellent Terran bot that amazed me a lot. I'm also very interested to see if Cherry Pi uses any machine learning methods in AIIDE 2018.


AIIDE Specific Question:

Q: Do you feel that the current format of iterated round-robin win percentage
   is a good indicator of bot skill ranking? If not, how would you change it?
   >> Yes, I think it is a good indicator of bot skill ranking.