Ah right, so if you mean algorithms then just say so. No, it's not hundreds. You would need millions or billions of generations to beat a player. You seem to be a bit misinformed about how it works. The most common AI learning is stacking a massive database about every possibility with given controls. At first is literally just spamming every combination possible and seeing what happens. Now let's come back to the chess. In chess there are 400 different positions after each player makes one move apiece. There are 72,084 positions after two moves apiece. Since TB has 18 joints and 4 states each as we established, that's 72^72 of combinations, so in toribash there are 5.3E133 different positions EVERY MOVE. So, it would take billions of generations for an AI to beat a player in Toribash, and even that is very optimistic since I'm still not involving the fact that the machine has to predict other player, which would probably take millions of games to build up big enough database about how typical player acts.
So yes, as you said 100kb for an average aikido game, now let's include the database of moves to predict + the database of all the past moves to reference and you're looking at thousands of gigabytes of data. Can your home computer process that much information in around 20 seconds that the frame allows you to edit your tori? Even a supercomputer would probably need some personalised tweaking to run an AI such as this one.
Btw in GTA you don't need to predict where other cars are going in a way that they are other, hard coded AIs with very predictable patterns.
And you're right, I don't have any experience at machine learning, it's just my own research and common sense.
So yes, as you said 100kb for an average aikido game, now let's include the database of moves to predict + the database of all the past moves to reference and you're looking at thousands of gigabytes of data. Can your home computer process that much information in around 20 seconds that the frame allows you to edit your tori? Even a supercomputer would probably need some personalised tweaking to run an AI such as this one.
Btw in GTA you don't need to predict where other cars are going in a way that they are other, hard coded AIs with very predictable patterns.
And you're right, I don't have any experience at machine learning, it's just my own research and common sense.
Last edited by Smaguris; Jul 4, 2018 at 11:50 PM.
I looked into this a while ago. First thing I did was research existing work done and found out some guys put together a pretty solid artifical move maker using genetic algorithms and lua scripts for a research project. Pretty neat, but not what we're after.
My vision was to create a program though that would take in a load of replays and learn from those to be able to play a particular mod for example. The first problem with something like that is just amassing enough data to actually train the model in the first place. I put in a request to get a download of all/any aikido games played that were cached or saved anywhere but apparently nothing like that exists.
So we're stuck at the first hurdle there.
Two possible solutions to kick off that first step:
1. Community source the replays. Get as many people as possible to upload all their replays that meet the parameters of what we're looking for. The main issue is that there probably still wouldn't be near enough data and it requires effort for people to contribute. Even if you made a script to crawl the replays section and grab all replays and later filter them for desired parameters you'll probably be short.
2. Create a script that connects to the toribash servers and "watches" games being played in rooms. This involves knowing the protocol to connect to the servers and read game data into a usable format that we can then use to train our machine. I did look into this back a bit and I think with a bit of work should be possible. Then let it run, recording games of the mod you want until you have enough data.
Then from there try to see if we can teach the machine.
This is still not at all trivial. Unlike something like chess where one piece moves to one location each turn, Toribash has 2 players moving simultaneously in 3D space with lots and lots of possible combinations each turn.
For each player:
21 joints with 4 states each = 4^21
And then x2 and x2 for hands gripped/ungripped.
That's...a lot of possible states, and just for one player.
I'm not super well versed in machine learning so I can't really comment on how much of a problem that is but my guess would be that it's on the side of making things harder rather than easier.
My vision was to create a program though that would take in a load of replays and learn from those to be able to play a particular mod for example. The first problem with something like that is just amassing enough data to actually train the model in the first place. I put in a request to get a download of all/any aikido games played that were cached or saved anywhere but apparently nothing like that exists.
So we're stuck at the first hurdle there.
Two possible solutions to kick off that first step:
1. Community source the replays. Get as many people as possible to upload all their replays that meet the parameters of what we're looking for. The main issue is that there probably still wouldn't be near enough data and it requires effort for people to contribute. Even if you made a script to crawl the replays section and grab all replays and later filter them for desired parameters you'll probably be short.
2. Create a script that connects to the toribash servers and "watches" games being played in rooms. This involves knowing the protocol to connect to the servers and read game data into a usable format that we can then use to train our machine. I did look into this back a bit and I think with a bit of work should be possible. Then let it run, recording games of the mod you want until you have enough data.
Then from there try to see if we can teach the machine.
This is still not at all trivial. Unlike something like chess where one piece moves to one location each turn, Toribash has 2 players moving simultaneously in 3D space with lots and lots of possible combinations each turn.
For each player:
21 joints with 4 states each = 4^21
And then x2 and x2 for hands gripped/ungripped.
That's...a lot of possible states, and just for one player.
I'm not super well versed in machine learning so I can't really comment on how much of a problem that is but my guess would be that it's on the side of making things harder rather than easier.
Of course its possible with appropriate qualifications.There is a lot of AI's with very effective learning program.I think chess is more competitive ,but its nothing for the AI with "Artificial Intelligence"
I was reading a post about the facebook Artificial Intelligence.This program was stopped by the scientists.The AI created his own language wich is very dangerous.
Of course the toribash AI will be way easier than this.
Solax idea is possible but I think its a little harder than this
I was reading a post about the facebook Artificial Intelligence.This program was stopped by the scientists.The AI created his own language wich is very dangerous.
Of course the toribash AI will be way easier than this.
Solax idea is possible but I think its a little harder than this
LEADER OF ABSOLUTE SANCTUM
RECORD HOLDER
Originally Posted by Solax
So we're stuck at the first hurdle there.
Two possible solutions to kick off that first step:
1. Community source the replays. Get as many people as possible to upload all their replays that meet the parameters of what we're looking for. The main issue is that there probably still wouldn't be near enough data and it requires effort for people to contribute. Even if you made a script to crawl the replays section and grab all replays and later filter them for desired parameters you'll probably be short.
2. Create a script that connects to the toribash servers and "watches" games being played in rooms. This involves knowing the protocol to connect to the servers and read game data into a usable format that we can then use to train our machine. I did look into this back a bit and I think with a bit of work should be possible. Then let it run, recording games of the mod you want until you have enough data.
The issue with this is that the machine doesn't learn from itself at all in both scenarios. While "studying" replays isn't half bad idea, it means it could pick up just as many bad tactics and moves as good ones, which would get it nowhere.
Starting off with sourcing few thousand replays is definitely the right thing to do, but it's only the first and smallest step. The machine would still have to play tens of thousands of games to "realise" which moves are superior to others or how to counter a certain move. The "countering" part would probably be extremely hard to overcome because it requires acting against what ghost is suggesting. It creates a massive spiral of checking previous games to guess what the opponent is going to do, and even then all it can act against is the most statistically probable outcome. Anything that the opponent does out of the ordinary instantly throws off the AI because it can't act on statistical probability no more.
Idk to me it seems like all too much for a system to handle at this point. Maybe after 10-20 years this would be possible from a home computer, but now it would require loads and loads of processing power. This sort of AI would have to update its database constantly with no end to it since there are infinite sets of moves that can be done every match.
Last edited by Smaguris; Jul 5, 2018 at 10:45 PM.
I'm a software engineer, and creating an AI for TB really depends on what information can you extract from the API, if there is even one.
You have to take into account the 4 joint states of all the joints to map what might happen in the next x frames the mod is set to use in a turn, plus you have to factor in collision effects, but otherwise there is a limited number of states (4^40 = 1208925819614629174706176, basically a metric fuckton) you'd have to investigate if you want your bot to have the best winrate possible.
If it was possible to have this done in a reasonable amount of time, what you'd need to do is see which state gets you closer to victory in the majority of scenarios (so 4^20 per state you can choose, 4^40), be that more points or your opponent getting closer to disqualification and just roll with that. Optimal (short term) play by the bot would follow. You can improve this by calculating each possibility for the next turn, and the next turn, and so on, and choose your move based on that extended map instead.
Really resource-intensive, but this bot could play TB even if the guy making it couldn't.
You can simplify this model by introducing openers / pre-set moves, limiting the scenarios you investigate per turn, etc.
Edit: fractures and DMs obviously reduce the amount of calculations needed.
You have to take into account the 4 joint states of all the joints to map what might happen in the next x frames the mod is set to use in a turn, plus you have to factor in collision effects, but otherwise there is a limited number of states (4^40 = 1208925819614629174706176, basically a metric fuckton) you'd have to investigate if you want your bot to have the best winrate possible.
If it was possible to have this done in a reasonable amount of time, what you'd need to do is see which state gets you closer to victory in the majority of scenarios (so 4^20 per state you can choose, 4^40), be that more points or your opponent getting closer to disqualification and just roll with that. Optimal (short term) play by the bot would follow. You can improve this by calculating each possibility for the next turn, and the next turn, and so on, and choose your move based on that extended map instead.
Really resource-intensive, but this bot could play TB even if the guy making it couldn't.
You can simplify this model by introducing openers / pre-set moves, limiting the scenarios you investigate per turn, etc.
Edit: fractures and DMs obviously reduce the amount of calculations needed.
Last edited by ynvaser; Jul 8, 2018 at 02:52 PM.
