Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

2015 AIIDE Starcraft AI Competition – Report and Results

webdocs.cs.ualberta.ca

Post reply on HN
Print view View original

1–10 of 42 posts

Re: 2015 AIIDE Starcraft AI Competition – Report and Results

#2

Post by krasi0 »

Some more useful links for those who are interested to learn more:

BWAPI GitHub page [0]

StarCraft Broodwar AI development Wiki[1]

The obligatory IRC channel where we discuss random topics concerning AI development[2]

[0] https://github.com/bwapi/bwapi

[1] http://www.starcraftai.com/wiki/Main_Page

[2] http://webchat.freenode.net/?channels=BWAPI

Re: 2015 AIIDE Starcraft AI Competition – Report and Results

#4

Post by narsil »

The faq links for each bot are interesting. The author of the bot ranked first (Tscmoo) doesn't think the bot uses any interesting AI techniques or algorithms: https://dl.dropboxusercontent.com/u/23817376/Starcraft/AIIDE...

> My bot has a variety of different strategies that it can execute. The strategy to execute is chosen randomly using weights, and the weights are adjusted based on previous match results. It's pretty simple but I guess it could be called learning.

The top 3 bots are independent entries, and beat the bots using learning algorithms such as UCB1 from research institutions. The author of the bot ranked second does think that other bots that minimized hand-crafted solutions would be more interesting: https://dl.dropboxusercontent.com/u/23817376/Starcraft/AIIDE...

Re: 2015 AIIDE Starcraft AI Competition – Report and Results

#6

Post by kzrdude »

narsil wrote: post #4

The faq links for each bot are interesting. The author of the bot ranked first (Tscmoo) doesn't think the bot uses any interesting AI techniques or algorithms: https://dl.dropboxusercontent.com/u/23817376/Starcraft/AIIDE... > My bot has a variety of different strategies that it can execute. The strategy to execute is chosen randomly using weights, and the weights are adjusted based on previous match results. It's pre…

The winner is very interesting, while the runner up uses the simplest possible strategy every single game. The runner up had a favourable record against the winner too, but lower win percentage overall. Thank goodness the more interesting one could win.

Basically, 4 pool beats all but one of the bots in the game over 50% of the time (often above 80-90%).

Re: 2015 AIIDE Starcraft AI Competition – Report and Results

#7

Post by llasram »

narsil wrote: post #4

The faq links for each bot are interesting. The author of the bot ranked first (Tscmoo) doesn't think the bot uses any interesting AI techniques or algorithms: https://dl.dropboxusercontent.com/u/23817376/Starcraft/AIIDE... > My bot has a variety of different strategies that it can execute. The strategy to execute is chosen randomly using weights, and the weights are adjusted based on previous match results. It's pre…

I'd noticed too that the winner claimed to use just a variety of hand-rolled strategies, and wonder why that is. Has anyone had the time to dig into the code? Is this a case of well-writen "naive" code trumping theoretically-better but poorly-implemented algorithms, or are there properties of the game state-space which make e.g. Monte Carlo tree search perform poorly?

Re: 2015 AIIDE Starcraft AI Competition – Report and Results

#8

Post by Havoc »

llasram wrote: post #7
narsil wrote: post #4

The faq links for each bot are interesting. The author of the bot ranked first (Tscmoo) doesn't think the bot uses any interesting AI techniques or algorithms: https://dl.dropboxusercontent.com/u/23817376/Starcraft/AIIDE... > My bot has a variety of different strategies that it can execute. The strategy to execute is chosen randomly using weights, and the weights are adjusted based on previous match results. It's pre…

I'd noticed too that the winner claimed to use just a variety of hand-rolled strategies, and wonder why that is. Has anyone had the time to dig into the code? Is this a case of well-writen "naive" code trumping theoretically-better but poorly-implemented algorithms, or are there properties of the game state-space which make e.g. Monte Carlo tree search perform poorly?

I think its just a case of this still being pretty difficult. So a decent handcrafted strategy will beat a computer generated one in a tournament.

Re: 2015 AIIDE Starcraft AI Competition – Report and Results

#10

Post by FanaHOVA »

Really interesting, I started playing on SC2 so I'm not sure about the dynamics of BW but I wonder how the lack of micro skews the results. For example a fast reaper push hopping on/off the enemy base can't probably be done by a bot. Terrans are also much easier to automate, while Zergs require microing with injections, etc are the demos uploaded anywhere?
Post reply on HN