Talk:BeepBoop

From Robowiki
Jump to navigation Jump to search

Contents

Thread titleRepliesLast modified
Energy Management & Firepower Selection222:49, 23 June 2021
Awesome enty2317:57, 23 June 2021
First page
First page
Next page
Next page
Last page
Last page

Energy Management & Firepower Selection

You know, your description of using score estimation based firepower selection, reminded me that back in 2010-2011 I was working on a thing akin to that for Midboss. I'd commented on it some I'm sure, but don't think I ever described it in great deal, nor shared the code. I find it interesting to compare what I built back then to what BeepBoop is doing.

Posted it here now for interest's sake: Midboss/Score-Estimation_based_Firepower_Selection

It had some score estimation formulas that were pretty similar to BeepBoop's.... but one key difference made is far far slower. It performed that score estimation formula absurdly many times per tick. Rather than be content with some continuous-time estimate based on average rate of damage, it did brute force prediction of discrete future waves, all the permutations of hits/misses, for up to 30 waves into the future (though with caching to effectively re-join alike branches, since 2^30 would get silly), only performing the sort of score estimation BeepBoop does at a depth or minimum probability limit.

I'm not sure how much extra going for simulating discrete branching possibilities with discrete waves gained me, but the idea was that it this would give it some more potential for interesting emergent 'cleverness', such as around the precise timing of things or amount of energy left for firing toward the very very end of the round. Boy did it chew up CPU though.

The fact that BeepBoop is using a form of score estimation in it's firepower selection, tempts me to some day go back to try to refine what I had started back then, so thanks :-)

Rednaxela (talk)11:01, 23 June 2021

That's really cool, I didn't see that! I also built a bullet power simulator that took into account discrete firing, bullet flight time, etc. However, it didn't use tree search: I just did monte-carlo rollouts of running it a couple hundred times and averaging the results, so it's probably much slower than yours! It's not used in BeepBoop, but I did use it to validate that BeepBoop's fast estimates assuming continuous time, normal distribution for hitrate, etc. were about right. For example, here and here are some plots showing that BeepBoop's approximations work pretty well, although not perfectly and with some edge cases (it says file uploads are disabled so I can't add them to the wiki). I sometimes see interesting emergent behavior from BeeBoop like firing high-power bullets when it's losing, presumably either to get more bullet damage and take less bullet damage before it dies or in the hope that a lucky high-power hit turns things around.

--Kev (talk)18:31, 23 June 2021

I think I got uploading working... give it a try and let me know.

Skilgannon (talk)22:49, 23 June 2021
 
 

Awesome enty

This new bot of yours really is awesome ! It is really beating the hell out of the topbots, even without BulletShielding.

Alas I am not able to run any battles for it, as I am still on Java 8.

GrubbmGait (talk)14:48, 19 May 2021

Thanks! I will make it Java 8 compatible for the next release.

--Kev (talk)01:17, 20 May 2021

Just wanted to add to this thread, this robot truly is a beast! Congratulations on 100% PWIN!

Slugzilla (talk)05:20, 23 May 2021
 

alas, in version 0.11, still some parts are not Java 8 compatible: kc/mega/game/Battleffield has been compiled by version 57.0.
Does not matter that much, I am just not able (currently) to run any battles for it. Same for Raven as it has been compiled by version 55.0.

GrubbmGait (talk)12:14, 5 June 2021

Oops, I will have another go at fixing it for my next release!

--Kev (talk)07:58, 6 June 2021

I've downloaded Java 13, I can now run battles for BeepBoop. After rebuilding the robot-database, also Raven and WaveShark run fine. Note that for my development I will still use the compiler option '-source 1.8'

GrubbmGait (talk)12:14, 7 June 2021

Ok, great! I compiled 0.11 with --release 8, but I think it didn't work because there were some old .class files lying around that didn't get overridden.

--Kev (talk)23:49, 7 June 2021
 
 
 
 

Oh wow, missed this! Awesome work Kev, you have a history of popping up with surprise entries =)

I'd be curious to know more about the Tensorflow work you did to make the KNN features...

Skilgannon (talk)22:26, 13 June 2021

Thanks! I wrote a brief description under BeepBoop/Understanding_BeepBoop, but I'll release the code too once I get it cleaned up.

--Kev (talk)00:13, 15 June 2021

Aha, I missed the last section. Surprised there wasn't more to gain from some kind of deeper embedding model.

Skilgannon (talk)10:28, 15 June 2021

Me too, and I'll maybe revisit it at some point. Theoretically a deeper embedding model could learn feature interactions like "wall-ahead is more important when velocity is 8 than when it is 0"

--Kev (talk)20:33, 20 June 2021

I’m surprised as well. Btw, how many layers are you using in the deeper model? And is that fully connected? I guess some deeper models with explicit feature interactions may work better in robocode scenario, given high noise. I would try things like Deep&Cross, DeepFM, etc.

Xor (talk)06:31, 21 June 2021
 

It's possible that the KNN already takes that into account sufficiently. Maybe if you bump the cluster size up a lot, and change the kernel width for cluster weighting, it might force this part of the learning into the NN instead?

Skilgannon (talk)14:06, 21 June 2021
 
 
 
 

Yeah, very cool to see! Congrats from me, too! And I'm enjoying reading about it.

Voidious (talk)16:29, 18 June 2021

Hey Voidious, long time no see! Glad you enjoyed reading about it, I learned a lot from Diamond's code while developing BeepBoop.

--Kev (talk)20:31, 20 June 2021
 
 
First page
First page
Next page
Next page
Last page
Last page