News for hackers. Stuff that matters.
Re:Show HN: Self-taught neural network learns to shoot a target by eerrt on Sunday January 05, 2020 @01:29PM (#21962926)
Am I the only one who thinks this is a little overengineered?
Re:Show HN: Self-taught neural network learns to shoot a target by ssivark on Sunday January 05, 2020 @01:34PM (#21962953)
Not unlike most neural network solutions :-P

But hey, this seems to be a fun project more than anything else. And working in such low-dimensional spaces with an obvious disentangled representation (only shot strength and angle matter) might provide intuition to beginners.

Re:Show HN: Self-taught neural network learns to shoot a target by atum47 on Sunday January 05, 2020 @01:46PM (#21963054)
yeah, I'm thinking about stealing wind strength and direction from the Worms game
Re:Show HN: Self-taught neural network learns to shoot a target by verst on Sunday January 05, 2020 @03:33PM (#21963851)
Remember Gorillas from the QBasic language? That had wind speed and direction. Perhaps helpful.

https://github.com/GorillaStack/gorillas/blob/master/gorilla...

Re:Show HN: Self-taught neural network learns to shoot a target by goldenkey on Monday January 06, 2020 @05:38AM (#21968099)
Gunbound was extremely complex with all kinds of variables including boomerang style projectiles.
Re:Show HN: Self-taught neural network learns to shoot a target by atum47 on Sunday January 05, 2020 @03:25PM (#21963794)
think about it like this:

with a 10 minutes training the neural network takes about 8 shots to hit the target, so as the player, you have 8 shots to hit it before it hits you.

after 20 minutes of training the nn would take about 4 shots to hit you... so on and so forth.

the original idea was to have several levels of difficulty and distribute them across the game levels.

levels 1-10 poorly trained nn levels 2-20 better trained nn levels 30 and above you got one shot before the nn hits you.

anyway, it was just an idea

Re:Show HN: Self-taught neural network learns to shoot a target by rs23296008n1 on Sunday January 05, 2020 @05:57PM (#21964808)
Never just an idea. Remove the "just". It is a realised idea and it was important that you execute the idea and, to whatever useful extent, finish it. Don't allow that negative wordplay. Don't make light of this and think there are no consequences in keeping that diminishing, passivity inducing "just".
Re:Show HN: Self-taught neural network learns to shoot a target by jeffshek on Monday January 06, 2020 @08:46AM (#21969045)
This is the light that shines through cynicism - the light that makes people brave enough to post new stuff.
Re:Show HN: Self-taught neural network learns to shoot a target by atum47 on Sunday January 05, 2020 @07:49PM (#21965501)
I'll remember that. Thanks
Re:Show HN: Self-taught neural network learns to shoot a target by stanfordkid on Sunday January 05, 2020 @10:34PM (#21966214)
On point! So much harder to execute and create something real and tangible than pontificate.
Re:Show HN: Self-taught neural network learns to shoot a target by armatav on Tuesday January 07, 2020 @01:17PM (#21982789)
This poster is correct - “just” takes away from yourself, it’s an idea.
Re:Show HN: Self-taught neural network learns to shoot a target by darepublic on Monday January 06, 2020 @12:00PM (#21970717)
well its kind of a hello world-ish example within this domain so I am fine with it
Re:Show HN: Self-taught neural network learns to shoot a target by atum47 on Sunday January 05, 2020 @01:44PM (#21963036)
probably not