Poisoning Enemy Learning Systems
The highlighted comment was created in this revision.
I just ran across an interesting article:
That's pretty interesting stuff, and not just in relation to Robocode.
As for Robocode applications, poisoning the enemy's guns with data also carries the risk of not dodging bullets, since the data gathering and the classification are so intertwined. But it's the type of technique you'd only use against high level opponents, like we do with flatteners, so it's already a situation where you're not able to dodge very accurately.
But I wonder... One thing it mentions is that this is possible if you have access to the same data as the enemy. In Robocode, of course we do, technically. But if that were really true, we'd be able to emulate the enemy's gun stats and do perfect curve flattening and never get hit. So I think it's probably closer to true that we don't have access to the same data as the enemy.
Actually it is possible to emulate opponent guns unless they use some pseudo-random technique. But we don't perfectly emulate because there are many different guns from many different opponents and few bots try to classify and specialize against the bot it is battling against (i.e. ScannedRobotEvent.getName()). Generalist bots are more fun.
Interesting fact is, this concept is already being used in RoboRumble for years.
PatternMatching (learning)... Anti-pattern matching (counter-learning)... GuessFactors (learning)... FlatMovement (counter-learning)... Dynamic Clustering... data decay...
In some sense, we are at the bleeding edge of AI advancement. There are very few AI competitions with imperfect information around the world other than Robocode. I can only think of one or two.
Basically what they explains is ways to use the minimum of 'false' information (in Robocode terms that means intentionally skewing your movement profile, but with increased chance of getting hit) in order to maximize the chance that they will incorrectly classify future data (ie, aim in the wrong place next time).
I agree anti-pattern matching and anti-GF have been effective at dodging their specific type of targeting, however this is a different concept entirely. This is about intentionally behaving in a certain way so that they will think you will do this next time, not behaving that way because you know exactly where they will shoot.
I would love to apply this somehow, because I think our learning guns are very susceptible to this. Sure, they all shoot differently at surfers meaning you can't take one gun and dodge another, but when you consider a movement profile with obvious peaks they all tend to shoot in the same way. Our wavesurfing flattens the profile, but all that does is bring us to the edge cases where every gun will shoot differently. If instead we have peaks that are obvious, all of the guns will shoot in the same way, making it possible to better predict their bullets and thus dodge them more reliably.
